| Link(s) | Title | Author(s) | Source | Abstract | |
|---|---|---|---|---|---|
| Barredo Capelot, E. and Buono, D. | Proc. International Statistical Institute (ISI) World Statistics Congress | Parallel advances in IT and in the social use of Internet-related applications, provide the general public with access to a vast amount of information. The digital revolution has emphasized the importance for policy-makers and economic agents of a real-time assessment of the current state of the economy. The associated Big Data are potentially very useful for a variety of applications. From the point of view of official statistics, the main question is whether and to what extent Big Data are a field worth investing to expand, check and improve the data production process and which types of partnerships will have to be formed for this purpose. In this paper we present the results and main recommendations from the Eurostat-funded project which benefits from the cooperation and work of the Eurostat and external academic experts. The project focused on the particular case of using Big Data for macroeconomic nowcasting, thus possibly enhancing the timely availability and precision of early estimates of key macroeconomic variables, and potentially providing new Big Data based coincident and leading indicators of economic activity. In a nowcasting context, Big Data provides potentially relevant complementary information with respect to standard data, being based on rather different information sets. Moreover, it is timely available and, generally, not subject to subsequent revisions – all relevant features for indicators providing information about the current state of an economy. Furthermore, it can provide a more granular perspective on the indicator of interest, both in the temporal and in the cross-sectional dimensions. While it is clear that there is a potential for an important contribution in this context, Big Data raises a number of old and new issues, first of all related to the availability of relevant data, as well as the continuity and quality of its provision. In this context, the establishment of reliable partnerships with data providers, both in the public and the private sector, as well as with the research community, could represent a critical factor of success. | |||
| Bikauskaite, A., Götzfried, A. and Völfinger, Z. | Statistika, 99 (1), pp. 69-76 | Globalisation presents significant statistical challenges, particularly for small and open economies in terms of measuring statistical indicators and communicating the results to users. The European Statistical System allocated high priority to the better measuring of globalisation in the statistical processes and output, in business or macro-economic statistics. Some concrete actions were already undertaken such as setting up of the EuroGroups Register of multinational enterprise groups and the putting in place of a so-called Early-warning System for monitoring restructurings of the groups. This paper focuses on the EuroGroups Register (EGR), the central statistical business register of Eurostat and the EU and EFTA countries' statistical authorities. The EGR is part of the EU statistical infrastructure and has been built up to better capture globalisation effects as well as for improving the consistency of national data on enterprise groups 4 . | |||
| Bujnowska, A. | Data-Driven Policy Impact Evaluation – How Access to Microdata is Transforming Policy Design, pp. 87-99 | The chapter presents the European microdata access system. This system allows eligible researchers to analyse detailed data transmitted to Eurostat by national statistical offices in the European Union. Eurostat is a single entry point of access to such data. Individual data collected by national statistical offices to produce official statistics are strictly confidential. The data are anonymised and further processed before they can be made available for scientific purposes. Statistical offices are legally obliged to protect information received from individual respondents. They use this information solely to produce official statistics. The entities collecting data for other purposes (e.g. administrative, commercial or health) fall into the scope of personal data protection legislation. Statistical confidentiality measures are stricter than those resulting from personal data protection measures. | |||
| Descy, P., Kvetan, V., Wirthmann, A. and Reis, F. | Statistical Journal of the IAOS, 35 (4), pp. 669-675 | Following the increasing penetration of the internet, the number of websites that advertise jobs is growing. The European Centre for the Development of Vocational Training (Cedefop) and the ESSnet Big Data have engaged in parallel projects to assess the feasibility of using online job advertisements (OJA) for labour market analysis and job vacancy statistics. After an initial feasibility study finalised in 2016, Cedefop is developing a Pan-EU system providing information on skills demand present in OJA, which will be operational by 2020. The ESSnet has focussed on statistics that can be derived from OJA and entered into a second phase in November 2018 aiming at creating the conditions for a larger scale implementation of the use of OJA in official statistics. This paper builds on experiences gathered in both projects and identifies opportunities and limitations of using OJA for the above-mentioned purposes. In addition, it discusses the feasibility of creating a joint system for processing and analysing OJA data based on discussions that have taken place in the past two years between Cedefop and the ESSnet Big Data on both projects. In this respect, this paper outlines a possible partnership between Cedefop and the European Statistical System to create and manage a unique source of OJA data that would serve multiple uses in the domain of labour market analysis and official statistics. It presents potential types of (statistical) data and variables based on the information contained in OJAs at European, national and regional levels. Data limitations linked to OJAs nature and specificities will be stressed, too. The paper concludes that there is high potential for combining institutional efforts and creating a joint data collection and processing system on OJA and intends to feed a discussion on the feasibility and the implications of creating a European system for OJA, which can serve European and national needs. | |||
| Grazzini, J., Gaffuri, J. and Museux, J.-M. | Proc. New Techniques and Technologies for Statistics (NTTS) | Opening up data obviously provides the opportunity to involve actors from outside the European Statistical System - say produsers, e.g., statisticians, scientists, citizens - and promote innovative, user-centric ways to tackle new and existing policy issues by co-designing statistical products. This also has the potential to increase National Statistical Offices efficiency and effectiveness. However, open data alone does not automatically translate to public participation to the decision-making. In most data provision services, there is an overarching top-down ideology since statistical processes are still owned, dictated and designed by National Statistical Offices and the final users are only involved as the receivers of the data and/or services . We propose to move away from the current approach by providing tools and software for accessing and using online data, so as to enable sharing best practices, learning from others' experience, adopt common methodologies, enhance cooperation between data producers and data users, and further engage in Open Data-driven innovation. | |||
| Kotseva, M., Roubanis, N., Gaffuri, J. and Reuter, H.I. | Proc. International Statistical Institute (ISI) World Statistics Congress | The European Statistical System is a partnership between Eurostat (the Statistical authority of the European Union) and the National Statistical Institutes and other national authorities of the European Union Member States responsible for the development, production and dissemination of European statistics. The production of statistics relies on the Generic-Statistical-Business-Process-Model, which is enhanced with a Global Statistical Geospatial Framework. This creates an information infrastructure composed of statistical and geospatial information, which is connected and conceptually integrated to spatially enable all statistics throughout the entire statistical production process. A detailed (e.g. 1km grid), comparable (e.g. across countries) and efficient data production process provides the information required for analysis to contribute to the policy decision-making processes in the EU. To facilitate the implementation of the geospatial data strategy in the European Statistical System, Eurostat is active on various levels. At the European level, the “GEOSTAT” projects were launched (1km2 population grid for Europe; standardised, point-based, geospatial, reference framework for statistics; European adaptation of the Global Statistical Geospatial Framework). At the Member State level, separate actions were initiated to align the varying levels of the geospatial data available in the statistical production process. Specific objectives were facilitated within Eurostat by, for example, providing the necessary legal instruments (e.g. Census 2021 grid regulation, Integrated Farm Structure Statistics, etc.) and with the creation of pan-European geographical datasets. The presentation will report on Eurostat’s activities related to implementing a geospatial data strategy in the European Statistical System. | |||
| Lamboray, C. | Meeting of the Ottawa Group | The compilation of a CPI is often presented in two stages. First, prices are aggregated without weights at the elementary level. Prices are typically obtained from dedicated surveys for which price collectors visit outlets and record the observed prices. These elementary price indices are then aggregated to the higher levels using expenditure weights. Nowadays, CPIs are becoming a multi-source statistics where prices are obtained not only from price collection in the field but also from transaction data, administrative data or from the Internet using web scraping techniques. Depending on the data source, different strategies can be adopted for constructing the elementary aggregates and for compiling elementary price indices. A CPI may be compiled in more than two stages and weights may be available even within the elementary aggregates. With scanner data, the index compiler must make two main structural decisions which can have a significant impact on inflation measurement. First, the item which is being aggregated must be defined. Second, the level must be fixed up to which these items are first aggregated. To discuss this second issue, we distinguish two strategies for a category that can be divided into sub-categories. Either the items are directly aggregated to the category level, possibly using a multilateral method. Alternatively, the multilateral method aggregates only up to the sub-category level, and these intermediate sub-category level indices are then aggregated to the category level using for instance a Laspeyres-type index formula. The objective of this paper is to examine the impact of introducing this additional level of fixity in the CPI structure. | |||
| Luhmann, S., Grazzini, J., Ricciato, F., Meszaros, M., Giannakouris, K., Museux, J.-M. and Hahn, M. | Proc. New Techniques and Technologies for Statistics (NTTS) | This paper emphasizes the need for Official Statistics to go beyond current practice and exceed the limits of the National Statistical Offices and the European Statistical System to reach and engage with produsers - e.g. statisticians, scientists and citizens. Through the adoption of some best practices derived from the Open Source Software community and the integration of modern technological solutions, the "Shared, Transparent, Auditable, Trusted, Participative, Reproducible, and Open" principles can help create new participatory models of knowledge and information production. | |||
| Luhmann, S. | Proc. International Statistical Institute (ISI) World Statistics Congress | In an age of fake news and interpretable facts, it is of ever increasing importance to provide students with the tools they need to critically engage with the information presented to them. In many countries of the EU, statistics is an optional course though. So, in order to stimulate interest and spark curiosity that overcomes the many mental barriers statistics trigger in some new solutions had to be found. The DIGICOM project of the European Statistical System (ESS) set out to do just that. Its goal is to modernise the communication and dissemination of European statistics. This is achieved by exploring and developing innovative dissemination products and services based on experiences within the ESS and concrete needs of European statistics users. | |||
| Luhmann, S. | Proc. International Statistical Institute (ISI) World Statistics Congress | Information and knowledge are fundamental building blocks for all modern societies. Official statistics offer an information structure and a public good that responds to the needs of many categories of users - policy makers, citizens, teacher, NGOs, researchers and journalists. Yet, these audiences are not always aware of the products and tools that are at their disposal. To bridge this gap and respond to numerous future challenges of official statistics, the European Statistical System (ESS) has devised a common strategy - the ESS Vision 2020. As part of that strategy, Eurostat has set out to modernise the communication and dissemination of European statistics in close cooperation with National Statistical Institutes (NSIs) through the DIGICOM programme. Approaching communication in a holistic manner, DIGICOM focusses on four main areas of work: First, European users of official statistics are analysed to better understand them, their behaviour and their needs. This way, communication and dissemination can be targeted more precisely and interactions through various channels, including social media, can become more fruitful. Second, NSIs and Eurostat develop and share innovative statistical products. These are largely novel digital publications that make use of fresh visualization, animations, interactive tools and applications. Third, the project explores opportunities of open data dissemination. Particularly Linked Open Data technologies are examined to assess whether they can improve our discoverability and the reuse of official statistics. Finally, we enter into a dialogue with various groups of users in order to foster statistical literacy and promote the brand and the values of official statistics. As part of this, Eurostat together with 15 NSIs is organising a joint European Statistics Competition that reached over 11 000 students in 2018. The group is also is also pooling its efforts in gamifying and teaching statistics through e‐learning methods. | |||
| Mehrhoff, J. | Proc. International Statistical Institute (ISI) World Statistics Congress | As the global financial crisis has impressively shown, changes in real estate prices influence the health and soundness of the financial sector. However, the effective monitoring of the markets is severely hampered by the lack of comparable and reliable data. While good progress has been made as regards the compilation and dissemination of housing price statistics, the compilation of commercial real estate (CRE) price and associated indicators remains very challenging. Against this background and in the context of the G20 Data Gaps Initiative, Eurostat published in December 2017, under the auspices of the Inter-secretariat Working Group on Price Statistics (IWGPS), a Statistical Report on 'Commercial Property Price Indicators: Sources, Methods and Issues' that makes a first attempt at setting out the wide range of challenges linked to the measurement of CRE. | |||
| Mészáros, M. | Proc. New Techniques and Technologies for Statistics (NTTS) | A flag is an attribute of a cell in a data set that provides additional qualitative information about the statistical value of that cell. They can indicate a wide range of information, for example, that a given value is estimated, confidential or represents a break in the time series. Currently different sets of flags are in use in the European Statistical System (ESS). Some statistical domains use the SDMX code list for observation status and confidentiality status, OECD uses a simplified version of the SDMX code lists and Eurostat uses a short list of flags for dissemination which combines the observation and confidentiality status. While in most cases it is well defined how a flag shall be assigned to an individual value, it is not straightforward to decide what flag shall be propagated to aggregated values like a sum, an average, quantiles, etc. This topic is important for Eurostat as the European aggregates are derived from national data points. Thus the information contained in the individual flags need to be summarized in a flag for the aggregate. This issue is not unique to Eurostat, but can occur for any aggregated data. For example, a national statistical institute may derive the national aggregate from regional data sets. In addition, the dissemination process provides further peculiarity: only a limited set of flags, compared to the set of flags used in the production process, can be applied in order to make it easily understandable to the users. In the scientific community there is a wide range of research about the consequences of data aggregation but it concentrates only on the information loss during aggregation of information and there is no scientific guidance how to aggregate flags. This paper is an attempt to provide a picture about the current situation and provide some systematic guidance how to aggregate flags in a coherent way. Eurostat is testing various approaches with a view to well balance transparency and clarity of the information made available to users in a flag. From several options, 3 methods (hierarchical, frequency and weighted frequency) are implemented in an R package for assigning a flag to an aggregate based on the underlying flags and values. Since the topic has relevance outside of Eurostat as well, it was decided to publish the respective code with documentation with a view to foster re-use within the European Statistical System and to stimulate discussion, including with the user community. | |||
| Massarelli, N., Mayer, C. and Wirtz, C. | Proc. International Statistical Institute (ISI) World Statistics Congress | Eurostat has an experience of 15 years in using indicators to monitor progress towards sustainable development. Since 2017 it carries out a regular monitoring of progress towards the UN sustainable development goals (SDGs) in an EU context. This is a highly political exercise that attracts the attention of a wide and diverse audience. For this purpose, Eurostat coordinated the definition of an EU SDG indicator set in cooperation with a large number of partners and stakeholders and it oversees the yearly reviews of the set. Based on this indicator set, Eurostat produces yearly “monitoring packages”. These include several products and aim at reaching different groups of users, adapting content and communication style. | |||
| Oehler, F., Grundiza, S. and Tartamella, F. | Proc. International Statistical Institute (ISI) World Statistics Congress | Disparities in income, consumption and wealth (ICW) are increasingly analysed, not only by the research community and international organisations but also by the public. The joint distribution of income, consumption and wealth data provides links between the three economic dimensions. These data help to describe more thoroughly material well-being and households' economic vulnerability. Income and consumption aggregates drawn from national accounts (macro-level data) describe the situation of households as an institutional unit in the macroeconomic context. Income distribution (from the European Union Statistics on Income and Living Conditions, EU-SILC) and consumption data (from the Household Budget Survey), on the other hand, are based on micro-level data and used to measure inequalities in the context of social policies. Eurostat has been working on the two work streams of the ICW project: The joint distribution of ICW (based on household surveys) and micro (survey statistics) –macro (national account) data links for households' ICW. Differing concepts and data collection practices mean that the analysis of these different sources do not necessarily lead to the same conclusions as regards people’s prosperity. The work has been done in close cooperation with Organisation for Economic Co-operation and Development and European Central Bank. The paper describes the methods and results of the ICW project. The random hot-deck method was used for the statistical matching of ICW data from the surveys. By comparing micro- and macro-level statistics on households, we can understand their complementarities and differences and build robust links between the data sources. | |||
| Ricciato, F. and Bujnowska, A. | Proc. New Techniques and Technologies for Statistics (NTTS) | The modern society is undergoing a process of massive datafication. The availability of new digital data sources represents an opportunity for Statistical Offices (SO) to complement traditional statistics as well as to produce novel statistical products with improved timeliness and relevance. However, such opportunities come with important challenges in almost every aspect – methodological, business models, data governance,regulation, organizational and others. The new scenario calls for an evolution of the modus operandi adopted by SO also with respect to privacy and data confidentiality, that is the focus of the present contribution. We propose here a discussion framework focused on the prospective combination of advanced Statistical Disclosure Control (SDC) methods with Secure Multi-Party Computation (SMC) techniques. | |||
| Ricciato, F., Bujnowska, A., Wirthmann, A., Hahn, M. and Barredo-Capelot, E. | Proc. International Statistical Institute (ISI) World Statistics Congress | The availability of new digital data sources represents an opportunity for Statistical Offices (SO) to complement traditional statistics and/or deliver novel statistics with improved timeliness and relevance. Nowadays SOs are part of a larger "data ecosystem" where different organizations, including public institutions and private companies, engage in the collection and processing of different kinds of (new) data about citizens, companies, goods etc. In this multi-actors scenario it is often desirable to let one organization extract some output statistics (i.e., aggregate information) from input data that are held by other organization(s) in different administrative domain(s). We refer to this problem as cross-domain statistical processing. To achieve this goal, the most intuitive approach - but not the only one - is to exchange raw input data across administrative domains (organizations). However, this strategy is not always viable when personal input data are involved, due to a combination of regulatory constraints (including lack of explicit legal basis for data sharing), business confidentiality, privacy requirements, or a combination of the above. Furthermore, new data sources often embed a much more pervasive view about individuals than traditional survey and/or administrative data, an aspect that amplifies the potential risks of data concentration. In such cases, performing cross-domain statistical processing requires technologies to elicit only the agreed-upon output information (exactly or approximately) without revealing the input data. This entails addressing two distinct but complementary problems. First, we need to compute the desired output statistics without seeing the raw input data. Second, we need to control the amount of information that might be inferred about individual data subjects in the input dataset from the output. In the field of privacy engineering the notions of "input privacy" and "output privacy" are used to refer respectively to these two problems. We remark that these problems are separable, i.e., they can be addressed with distinct tools and methods that get combined together, overlaid or juxtaposed. In this contribution we review recent advances in both fields and briefly discuss their complementary roles. As for input privacy, we provide a brief introduction to the fundamental principles of Secure Multi-Party Computation (SMPC). As for output privacy, we review recent advances in the field of Statistical Disclosure Control (SDC). Finally, we discuss possible scenarios for SMPC and SDC integration in the future "confidentiality engineering" setup of modern official statistics. | |||
| Ricciato, F., Lanzieri, G. and Wirthmann, A. | Proc. workshop on the use of Administrative Data and Social Statistics | The concept of 'present population' is gaining increasing attention in official statistics. The (almost) continuous measurement of present population provides a basis to derive indicators of population exposure that are relevant in different application domains. One possible approach to measure present population exploits data from Mobile Network Operators (MNO), including CDR but also more informative (and complex) signalling records. Such data, collected primarily for network operation processes, can be repurposed to infer patterns of human mobility. Two decades of research literature have produced several case studies (mostly limited to CDR data) and a variety of ad-hoc methodologies tailored to specific datasets. Moving beyond the stage of explorative research, towards production of official statistics, requires a more systematic and sustainable approach to methodological development. Towards this aim, Eurostat and other members of the European Statistical System (ESS are working towards the definition of a general Reference Methodological Framework. In this contribution we report on the methodological aspects related to the estimation of present population density, for which we present a general and modular methodological structure. Along the way, we identify a number of specific research (sub)problems requiring further attention by the research community. | |||
| Rueda-Cantuche, J.M., Amores, A.F. and Rémond-Tiedrez, I. | Economic Systems Research | Every change in the product and/or industry classifications and/or methodology of supply, use and input-output tables makes any medium- to long-term policy analysis impossible unless appropriate conversions are provided by national statistical institutes using more detailed data. However, can these tables be reasonably converted to a different classification of industries and products using aggregate information? We develop a conversion method that allows changes in classification that are independent of the number of industries and products. In addition, we provide evidence about its empirical performance compared with projection methods. We find projection methods perform better than conversion methods, at least when using aggregate information. Nonetheless, unlike conversion methods, projection methods generally require supply, use and input/output tables in the new classification that might not always be available. In their absence, we recommend using more detailed and sophisticated data. | |||
| Rémond-Tiedrez, I. and Valderas Jaramillo, J.M. | Proc. International Input-Output Conference | Asymmetries due to the mismatching in the data provided by one country and the mirror flow provided by its partner country for the same transactions are an important issue in trade statistics, especially when it comes to link all European Union (EU) economies as in the FIGARO dataset. Although at EU level, balance of payments statisticians and trade in services statisticians follow up regularly on the asymmetries and try to reduce them, we needed to implement a methodology for compiling a balanced view of trade in services as an input to the EU inter-country supply, use and input-output tables.For the first release of FIGARO tables for the year 2010, the 2010 international trade in services data (ITSS) serves as the primary input. Their exports and imports (or mirror exports) are subsequently cleaned, imputed, estimated, modelled and confronted with Balance of Payments data to get a full dataset for 29 countries (EU Member States plus USA), 30 partner countries (plus RoW) and a number of services items. The balancing of the resulting exports and import values to solve the bilateral trade asymmetries is based on the methodology developed by the European Commission and the OECD. As the EU inter-country supply, use and input-output tables present economies using the activity and product classification, the last step is to bridge the balanced trade view of the data from services categories to product classification (CPA/CPC). The paper summarises the steps as compiled for the 2010 tables and shows the way foreseen to improve the compilation steps for the time series 2010-2016. We also evaluate the impact on the original input data of each of the steps involved. | |||
| Rueda-Cantuche, J.M., Velazquez-Afonso, A. and Rémond-Tiedrez, I. | Proc. International Input-Output Conference | The modular approach adopted in the construction of the EU inter-country supply, use and input-output tables (Figaro project) to map the different adjustments and imputations made to the original data allows each adjustment/imputation to be measured at the different stages of the compilation process. As a result, this paper provides summary statistics based on: the comparison between the international merchandise and services trade data adjusted for goods sent abroad for processing and merchanting activities and the trade values in the national available SUTs (i.e. discrepancies); the analysis of the row and column total discrepancies by countries, users and products; the analysis of the final balancing adjustments made to estimate the inter-country use table without discrepancies, by countries, users and products.This analysis provides useful information for the user of the FIGARO tables and helps producers in: highlighting the importance of the scope of some of the statistics they produce; identifying what type of data is still missing from national statistical offices; and identifying where to put more efforts in future revisions. All these aspects are relevant for the compilation process. | |||
| Ricciato, F. and Wirthmann, A. | Proc. Data for Policy conference | In this discussion paper we outline the motivations and the main principles of the Trusted Smart Statistics concept under development in the European Statistical System (ESS) to respond to the challenges posed by the prospective use of innovative digital data sources for the production of official statistics. | |||
| Ricciato, F., Wirthmann, A., Giannakouris, K., Reis, F. and Skaliotis, M. | Statistical Journal of the IAOS, 35 (4), pp. 589-603 | In this contribution we outline the concept of Trusted Smart Statistics as the natural evolution of official statistics in the new datafied world. Traditional data sources, namely survey and administrative data, represent nowadays a valuable but small portion of the global data stock, much thereof being held in the private sector. The availability of new data sources is only one aspect of the global change that concerns official statistics. Other aspects, more subtle but not less important, include the changes in perceptions, expectations, behaviours and relations between the stakeholders. The environment around official statistics has changed: statistical offices are not any more data monopolists, but one prominent species among many others in a larger (and complex) ecosystem. What was established in the traditional world of legacy data sources (in terms of regulations, technologies, practices, etc.) is not guaranteed to be sufficient any more with new data sources. Trusted Smart Statistics is not about replacing existing sources and processes, but augmenting them with new ones. Such augmentation however will not be only incremental: the path towards Trusted Smart Statistics is not about tweaking some components of the legacy system but about building an entirely new system that will coexist with the legacy one. In this position paper we outline some key design principles for the new Trusted Smart Statistics system. Taken collectively they picture a system where the smart and trust aspects enable and reinforce each other. A system that is more extrovert towards external stakeholders (citizens, private companies, public authorities) with whom Statistical Offices will be sharing computation, control, code, logs and of course final statistics, without necessarily sharing the raw input data. | |||
| Ricciato, F., Wirthmann, A. and Hahn, M. | Proc. Conference of European Statisticians (CES) | New types of digital data sources (or "big data") are now available as by-product of other technological processes. New data sources differ from the traditional data sources in use for official statistics, namely survey data and administrative records, along multiple dimensions. Therefore, the adoption of new data sources for the regular production of official statistics requires innovations at multiple levels, including new processing paradigms, computation methods, data access and governance models, staff skills, etc. The term "Trusted Smart Statistics" was put forward by Eurostat to indicate a comprehensive framework to evolve official statistics towards adoption of new data sources along with traditional ones. In this document we focus on the need to take a systemic view, and in general a system-design approach, towards the development of novel processing methodologies for new types of data. We argue for the need to identify selected 'classes' of new data types (e.g., mobile network operator data, smart energy meters, satellite images, etc.) and, for each class, to build a general Reference Methodological Framework as basis for developing specific methodologies for particular use-cases and statistical products. We discuss the principles that should inform the construction of such framework, and briefly report on the ongoing work being conducted at Eurostat for one particular class of data, namely mobile network operator data. | |||
| Sanz, A.F., Luhmann, S. and Moraleda, A.G. | AStA Wirtschafts- und Sozialstatistisches Archiv, 13, pp. 245-255 | Statistical literacy has become more and more important as the amount of available information grows. Providing people with tools that allow them to critically evaluate the information they receive is crucial in the world we live, especially for the youth. This, however, is not an easy task. Being capable of discerning which sources, data, information, analysis etc. are more reliable than others requires many times ‘not-so-light’ knowledge in traditionally ‘hard subjects’ like Mathematics, Economics or Statistics. In this context it is a good idea to offer students a friendly approach to these fields. Activities in which pupils see real data they can work with might help them to better understand what they have learnt and even to lose that fear of statistics. On the other hand, for official statistics bodies it is desirable to get known as reliable sources of data. Initiatives like the European Statistics Competition (ESC) pursues these two objectives of being made known among teachers and young public, and showing pupils that working with statistical data is feasible. The fact of being a competition at European level may encourage students to join and do their best, and thus their interest in statistics will grow. | |||
| Santos, M.J. and Pereira de Sá, C. | Proc. International Statistical Institute (ISI) World Statistics Congress | The European Parliament is a key player in the democratic process. The paper describes the multiple roles of the European Parliament in EU official statistics: providing a forum for political debate and decision-making; acting as a co-legislator adopting and amending legislative proposals; deciding on the EU budget together with the Council; supervising the work of the European Commission and other EU bodies; and cooperating with national parliaments of EU countries. | |||
| Sutcliffe, L.M.E., Schraml, A., Eiselt, B. and Oppermann, R. | Palaearctic Grasslands, 40, pp. 27-31 | The Land Use/Cover Area-Frame Survey (LUCAS) is a European inventory carried out every three years and coordinated by Eurostat. It aims to provide information for policy and science on land use, land cover and environmental parameters by surveying a statistically representative sample of points spread across the EU countries. In 2018, a new grassland module was piloted within the survey. This pilot aims to collect detailed information on the environmental and ecological quality of the grassland, as well as its type and intensity of use. Between April and July 2018, 3734 grassland points in 26 countries were surveyed using this standardised methodology. Of these points, 747 underwent an additional quality control to check the accuracy of the survey method. This is the first time a standardised methodology has been used to collect ecological data on grasslands in a coordinated manner over so wide a geographical range in Europe. The analysis of the data from this survey is ongoing, so the purpose of this article is to briefly describe the method used in the new grassland module and inform readers about how this pilot was developed. | |||
| Selenius, J., Wirtz, C., Florescu, D. and Lazar, A.C. | Proc. International Statistical Institute (ISI) World Statistics Congress | Information on the structure of agriculture is necessary to understand the risks for ensuring food security, the trends in food production as well as the impacts on rural life and the environment. At global level, the FAO advises all countries to carry out an agricultural census every 10 years to have a full picture of the situation. The European Union (EU) considers it necessary to collect data on farm structure for the common agricultural policy (CAP) and various other policies, often related to environmental aspects, but at more frequent intervals. This paper presents the technical and methodological aspects of the newly modified system for the European agricultural censuses. Under the new set-up, EU countries can reduce the burden on respondents while increasing the availability of statistics for the census 2020. A set of 184 core variables are collected as a census for all farms above common physical thresholds in all countries with the target of covering 98% of each country's agriculture. For sub-samples of farms, the core variables will be supplemented with variables grouped in three modules on ‘Labour force and other gainful activities’, ‘Rural development’ and ‘Animal housing and manure management’. The system allows countries to use multiple sources and methods - such as surveys, administrative data or innovative methods and approaches - to obtain data subject to meeting pre-defined quality requirements. The efforts of the European Statistical System (ESS) to allow countries who do not meet the census’s 98% agricultural area and livestock coverage requirements to conduct a sample data collection on the smallest farms and further ways of reducing costs and burden will be discussed. | |||
| Wirtz, C. | Proc. International Statistical Institute (ISI) World Statistics Congress | European legislation is omnipresent in agriculture, allowing to create standard administrative tools for controlling and monitoring the appropriate use of EU funds by keeping track of farmer activities. Eurostat cooperates with other European services in creating administrative systems that not only can also function as a data source, but that contain the information needed by the users. As geo-localised statistics are increasingly demanded, an important aspect is creating data sets that can be layered, thus reducing the need for complex data collection without losing analytical power. An important aspect of Eurostat strategies in the domain is creating European legislation that allows accessing and using any existing source or method for producing statistics, as long as the quality is good enough. This will allow reducing the burden on farmers and statisticians, while lowering the costs. | |||
| Bach, F. | Service-Oriented Mapping – Changing Paradigm in Map Production and Geoinformation Management, pp. 365-384 | This chapter outlines challenges and modern approaches in statistical disclosure control of official high-resolution population data on the example of the EU census rounds 2011 and 2021, where a particular focus is on the European 1 km grid outputs derived from these censuses. After a general introduction to the topic and experiences from 2011, the recommended protection methods for geospatial data in the planned 2021 census 1 km grids are discussed in detail. | |||
| Buono, D., Elliott, D., Mazzi, G.L., Bikker, R., Frölich, M., Gatto, R., Guardalbascio, B., Hauf, S., Infante, E., Moauro, F., Oltmanns, E., Palate, J., Safr, K., Tibert Stoltze, P. and Di Iorio, F. | In official statistics there is an increasing demand for indicators at a higher frequency than those that have traditionally been observed. Direct measures of indicators at a high frequency can be very costly and difficult to achieve sometimes resulting in low quality results when the information set is not adequate. In such situations temporal disaggregation techniques can constitute a feasible alternative to the direct estimation of high frequency indicators. Additionally, even when high frequency indicators can be directly compiled, they are often not consistent over time with lower frequency versions. For example, annual surveys with larger samples may give more accurate estimates of the level of a variable compared to estimates from a small monthly survey that is designed to provide estimates of monthly change. Under the hypothesis that low frequency indicators are more reliable than high frequency ones, benchmarking techniques can be used to ensure the time consistency between high and low frequency indicators. Finally, directly or indirectly measured high frequency indicators may not necessarily meet required accounting and aggregation constraints. If that low frequency indicators meet accounting and aggregation constraints, reconciliation techniques can be used to restore them on high frequency indicators too. Eurostat and the European Statistical System (ESS) developed these guidelines to help data producers derive high frequency data (e.g. quarterly or monthly) from low frequency data (e.g. annual) and to address related temporal and accounting constraints. Typical applications are known as temporal disaggregation, benchmarking, and reconciliation. The guidelines identify best practice to: (i) achieve harmonization across national processes; (ii) enhance comparability between results; (iii) ensure consistency across domains and between aggregates and their components. The establishment of common guidelines for temporal disaggregation within the European Statistical System (ESS) is an essential step towards better harmonization and comparability of official statistics, especially in macroeconomic indicators and labour market statistics. These guidelines address the need for harmonization expressed by users from European and National Institutions. This document presents both theoretical aspects and practical implementation issues in a user friendly and easy to read framework. They meet the requirement of principle 7 (Sound Methodology) of the European Statistics Code of Practice (CoP), and their implementation is consistent with principles 14 (Coherence and Comparability) and 15 (Accessibility and Clarity). The guidelines also provide transparency of temporal disaggregation, benchmarking and reconciliation practices by encouraging documentation and dissemination of practices. These guidelines are complementary to the ESS guidelines on seasonal adjustment (Eurostat, 2015 edition), the ESS guidelines on revision policy for PEEIs (Eurostat, 2013 edition), and the Eurostat and United Nations handbook on rapid estimates. They are also in line with the Handbook on quarterly national accounts (Eurostat, 2013 edition). |
||||
| Buono, D., Infante, E. and Mazzi, G.L. | Handbook on Seasonal Adjustment, pp. 669-680 | Most of the literature on business cycle analysis relies, as input, on the seasonally adjusted (SA) data of the main economic indicators. The rationale is that the seasonal frequencies are different from the frequencies of the cycles, then seasonal movements do not carry useful information, moreover they can hide the information on the frequencies of interest in business cycle analysis. This idea is coherent with the literature on SA that rests on the hypothesis of orthogonality among the seasonal and the others components. For several reasons this hypothesis can fail and an interaction between seasonal and business cycles can arise. This work address the plausibility of this hypothesis and a first study on the effect that different seasonal adjustment algorithms can have on the business cycle analysis due to their different ability in separating the seasonal from the other frequencies. Empirically the evidence or the presence of interactions can be hardly detectable. There are several reasons: components are unobservable as well as their connections, consequently. Moreover, the series are often characterized by instability, and/or evolutionary behaviour of the components. Aim of this work can be summarized in: empirical investigation of the effects of a variety of SA methods on two aspects: the cyclical shape of the series and the turning point dating. The focus is on the growth cycle. The approach will be historical, and then no real time exercises is run. | |||
| Bach, F., Kloek, W. and Bujnowska, A. | Proc. Quality conference | The protection of confidential information has a huge impact on how statistical data can be published and used for analysis, which makes it a key aspect of data quality. This paper presents new methods and tools currently being investigated in the ESS in order to publish more - and more useful - data without compromising statistical confidentiality. It covers new methodological and IT developments, where concrete use cases demonstrate their impact on data quality. For instance, a promising methodological direction is random noise: several ESS use cases at different maturity stages are presented, including recommendations for the harmonised protection of 2021 EU Census data. Another direction is to reflect at a more fundamental level where protection is needed. Several ideas will be presented along this line. | |||
| Florescu, D.C. | Proc. Quality conference | Eurostat, together with the statistical bodies belonging to the European Statistical System (ESS), has adopted a quality rating system to guide the dissemination of structural farm statistics derived from farm structure surveys. The system does this by showing when the estimates are sufficiently reliable to be published, either with or without a warning. It is based on: (i) coefficients of variations for totals and means of continuous variables; (ii) standard errors for proportions and counts. This paper also presents the work carried out to harmonise variance estimation methods and their application within the ESS. To apply the new quality rating system consistently, Eurostat and the national statistical bodies must compute roughly the same variance estimates. Future structural farm statistics will come from the data collected from 'Integrated Farm Statistics', based on a modular approach. This will lead to more complex national sampling designs. The paper also outlines ongoing developments towards integrating additional sampling design information specific to national multi-stage sampling in the estimation of variance. The paper also introduces new quality reporting based on the European Standard Quality Reporting System (ESQRS) template. This is of great help in assessing all quality dimensions, thereby improving the quality of EU data and metadata. Farm structure surveys are the main source of information on the current state of agriculture and the trends it is undergoing, required to monitor the common agricultural policy and other EU policies. High-quality data are essential for decision-makers. | |||
| Gaffuri, J. | Proc. Quality conference | Official statistics are often reported on statistical units, which are sometimes too large to depict properly the geographical distribution of the underlying phenomenon. In the European context for example, most statistics are produced only at national level (NUTS 0) and do not allow a true understanding of the spatial pattern at more local scales. Geographic resolution is a crucial component of quality in official statistics which should be better addressed. This article describes two experiments carried out at Eurostat for disaggregating statistics with auxiliary geographic data. These experiments are both based on dasymetric mapping: Input statistical values are distributed at the level of geographical features; these new statistical values are then re-aggregated at the level of target statistical units with a finer resolution. A first experiment was the disaggregation of tourism statistics over Europe from NUTS 2 to NUTS 3 and a 10km resolution grid. The auxiliary geographic information used is a database containing the location of around 160000 touristic accomodations over Europe. The outcome reveals a striking image of touristic activity over Europe, with spatial patterns which cannot be revealed at NUTS 2 level. The second experiment was on the disaggregation of mobile phone data over Belgium to assess population distribution on a 1km resolution grid. Mobile phone data are collected at antenna level, whose reception zones are extremely irregular in shape and size, especially in rural areas. Cadastral information on the location and volume of each single building over Belgium has been used to locate more precisely mobile phone users around built-up areas. Both experiments show the pertinence of using geographic information with dasymetric mapping method to improve quality related to geographical resolution. This method has been implemented in the generic library JGiscoTools (https://github.com/eurostat/JGiscoTools) and is intended be applied to other domains. | |||
| Gaffuri, J. | Proc. workshop of the ICA Commission on Generalisation and Multiple Representation | Railway data in OpenStreetMap are represented with a very high geometrical level of detail (less than a meter resolution). Using this data for spatial analyses at the European scale requires a simplification of this data to a scale of approximatively 1:50k. For such generalisation, we propose first to select only few of the elements available in OpenStreetMap. A suitable filtering procedure is proposed. We propose then to analyse the graph structure to ensure the main components of the network are selected and topological mistakes are corrected. A 'stroke' analysis is performed to select the main network sections. Finally, dual carriage ways and triage areas are simplified using some specific geometrical algorithms. The results obtained on a selected area (Sweden) are promising. | |||
| Grazzini, J., Lamarche, P., Gaffuri, J. and Museux, J.-M. | Proc. Quality conference | This contribution aims at further promoting the development and deployment of open, reproducible, reusable, verifiable, and collaborative computational resources in statistical offices regardless of the platform/software in use. Motivated by the consensus that data-driven evidence-based policymaking should be transparent, we argue that such approach is not only necessary for the practical implementation of statistical production systems, but also essential to reinforce the quality and trust of official statistics, especially in the context of a 'post-truth' society. We discuss some practical requirements to gear the continuous and flexible development and deployment of software components in production environments. Together with the adoption of some best practices derived from the open source community and the integration of new technological solutions, we propose to unleash the social power of open algorithms so as to create new participatory models of interaction between produsers that can contribute to a more holistic and extensive approach to production systems. Overall, a greater transparency in designing production processes is expected to result in a better grip on the quality of the statistical processes involved in data-driven policy-making. We illustrate this flexible and agile approach with various open, stand-alone software or source code used in statistical production environments at Eurostat. | |||
| Gatto, R., Ladiray, D. and Mazzi, G.L. | Handbook on Seasonal Adjustment, pp. 629-654 | Seasonal adjustment procedures are usually designed for being applied on sufficiently long time series in order to obtain good quality results. This is due both to technical reasons such as the properties of the symmetric filters used and to non-technical ones such as the fact that, over a sufficiently long time period, components can be better identified and separated; consequently, the seasonal component can be more precisely estimated and eventually removed. In addition, long time series are required in order to read properly the statistics of the seasonality tests. Furthermore, on short time series the seasonality tests might be less robust. In official statistics, available time series associated to statistical indicators are often relatively short or subject to some shortening processes. This seems to contradict one of the main quality dimensions of statistics which is the coverage, but, at the same time, official statistics need to be continuously improved to better reflect the socio-economic structure. This process unavoidably leads to regularly adapting existing official statistics to evolving socio-economic structure. Furthermore better reflecting the current socio-economic situation can also require the development and the statistical compilation of new indicators, which at least in a first phase will cover only a limited time span. These two processes imply, at least temporarily, the availability of short time series associated to the statistical indicators. | |||
| Grazzini, J., Museux, J.-M. and Hahn, M. | Proc. Conference of European Statistics Stakeholders (CESS) | While the importance of openness and transparency in statistical processes, and how these can be supported through open algorithms and open data, has been already emphasized, this contribution aims at showcasing an approach where algorithms and data are delivered as interactive, reusable and reproducible computing services. This will eventually provide produsers with the necessary tools to perform, for themselves, data analytics on Eurostat data in a straightforward manner. | |||
| Liotti, A. | Statistical Journal of the IAOS, 34 (3), pp. 313-316 | The main objectives of the Manual are: To provide guidelines for implementation of the EU Regulation; To support the harmonisation between the registers in the various Member States; To explain the Regulation's provisions. A recent survey has established that the statisticians in the European Statistical System dealing with the maintenance and development of national Statistical Business Registers find useful that they can find in the Manual the information necessary to allow the correct and consistent interpretation of the Regulation and recommendations on best practices of various countries in building and operating registers and in treatment of special cases. Users also appreciate that each chapter is capable of being read separately, whilst still forming part of a coherent set. The EU Regulation also legislates on the exchange of confidential data. This was the pillar on which was built the EuroGroups Register of multinational enterprise groups, managed by Eurostat with the participation of all European countries. A revision of the Manual will be necessary, in order to take on board the provisions of the upcoming new Regulation, as well as some new recommendations originated by the on-going Data Quality Programme for the Statistical Business Registers in the European Statistical System. | |||
| Marcellino, M.G., Papailias, F., Mazzi, G.L., Kapetanios, G. and Buono, D. | BAFFI-CAREFIN Centre (82) | This paper aims at providing a primer on the use of big data in macroeconomic nowcasting and early estimation. We discuss: (i) a typology of big data characteristics relevant for macroeconomic nowcasting and early estimates, (ii) methods for features extraction from unstructured big data to usable time series, (iii) econometric methods that could be used for nowcasting with big data, (iv) some empirical nowcasting results for key target variables for four EU countries, and (v) ways to evaluate nowcasts and ash estimates. We conclude by providing a set of recommendations to assess the pros and cons of the use of big data in a specic empirical nowcasting context. | |||
| Martins Ferreira, P., Rémond-Tiedrez, I. and Rueda-Cantuche, J.M. | Proc. International Input-Output Conference | Trade asymmetry has been a well-known fact and there are extensive literature and reports about the causes for those asymmetries. There is also a recognised effort made by trade statisticians for mitigate trade asymmetry over time. Notwithstanding the positive achievements that have been made so far, to build an Inter-Country Supply, Use and Input-Output tables (IC-SUIOT) we more than low trade asymmetry: we need no trade asymmetry at all. The European Statistical System (ESS) has an extensive and rich amount of trade data and a lot of resources are devoted to measure trade flows. Nevertheless, the customs union of the EU adds another challenge regarding trade in goods statistics: Member-States declare imports/exports for customs or tax purposes without thisMember State having acquired ownership of the goods, i.e. declare quasi-transit as well. While relevant for physical flow of trade, quasi-transit and re-exports distort the geographical economic relationship among Member-States and therefore they should be identified and taken into account in the framework of IC-SUIOT. QDR methodology was developed in order to address the specificities of trade in goods in EU by providing a way to estimate consolidated trade flows, i.e. solving trade asymmetries, between two countries by three types of trade: quasi-transit (Q), domestic (D) and re-export (R). For quasi-transit and re-exports the intermediary country between that takes part of the physical flow between origin and destination is also identified. QDR methodology was used in FIGARO project and it revealed very useful for identifying relevant trade relationships within countries. | |||
| Ricciato, F., De Meersman, F., Wirthmann, A., Seynaeve, G. and Skaliotis, M. | Proc. Conference of the Directors General of the National Statistical Institutes (DGINS) | This paper discusses various aspects related to the potential partnership between Statistical Offices (SO) and Mobile Network Operators (MNO) to leverage MNO data for the computation of official statistics.MNO data are complementary to other data sources that are already available to SOs (e.g., survey data, administrative registers)and their combination can lead to a new generation of statistical products, delivered more timely and with better spatio-temporal resolution than traditional statistics. This enables statisticians to gain more accurate and up-to-date insight into various aspects of human mobility and related socio-economic phenomena (e.g., tourism flows, presence and residence, commuting patterns, use of transportation means among others) with clear advantages for the process of policy design and evaluation based on such statistics.The cooperation between SO and MNO can be designed to prevent potential conflicts between the public and private interests, e.g. by the provision of adequate protection for business confidentiality, methodological quality and process transparency. We argue that partnering with SO brings direct and indirect benefits also to the MNOs, particularly in terms of empowering the portfolio of commercial analytic products they can offer to business customers. Synergies between the production of official statistics and commercial analytic products can be positively leveraged within the framework of a well-designed partnership model. By doing so, the SO-MNO partnership does not represent as a risk to the MNO business nor a diminution of the role and independency of SO, but rather as an additional opportunity for both sides. While the focus of this paper is on partnership models between SOs and MNOs, many elements of the discussion apply as well to private data holders from other sectors, and may contribute to advance the future vision of public-private partnerships for joint data analytics. | |||
| Ricciato, F. | Proc. Global Forum on Tourism Statistics | Mobile network signalling data, captured from the continuous interaction of mobile terminals with the cellular network, have better spatial/temporal resolution than traditional Call Detail records (CDR). However, their format and semantic are intimately connected with network-specific technical aspects. For this reason, such data are considerably more complex and have a higher degree of heterogeneity across different Mobile Network Operators (MNO). It is difficult for experts outside the telecommunication domains, such as e.g. statisticians, to interpret and manipulate such data directly. In the proposed contribution we present a general Reference Methodological Framework (RMF) intended to facilitate the use of signalling data by statisticians. The RMF is inspired by the principles of functional layering and by the "hour-glass model", which lie at the foundation of modern computer network architectures. The RMF encompasses a convergence layer that decouples the complexity of signalling data at the bottom from the statistical definitions on the top. This allows experts from the two domains, MNO engineers and statisticians, to work independently and eases the evolution of the two layers.This paper presents the general principles underlying the RMF, the role and responsibilities of the different actors in transforming elemental data into meaningful and relevant statistical concepts, provides a concrete actionable proposal and presents early results from its application in a pilot project conducted in collaboration between Eurostat and one European MNO. We highlight lessons learned and give an outlook for the future development and implementation of the RMF and its application to tourism statistics and other areas of statistics. | |||
| Rueda-Cantuche, J.M., Roman, M.V., Amores, A.F., Valderas Jaramillo, J.M. and Rémond-Tiedrez, I. | Proc. International Input-Output Conference | Services are increasingly delivered across borders under various modes of supply and gaining higher shares over all the economic activities. However, the availability of statistics on the international supply of services detailed by services category, mode of supply and partner country is limited and at the same time critically important for trade policy making. Based on the most recent Eurostat published data, this paper presents the first attempt to estimate the employment effects by modes of supply using official statistics and the Eurostat's experimental EU Inter-country Input-Output Table (FIGARO Project). | |||
| Rueda-Cantuche, J.M., Rémond-Tiedrez, I. and Bouwmeester, M.C. | Journal of Industrial Ecology, 22 (3), pp. 485-486 | Effective policy to encourage sustainable production and consumption is needed to shape the future so that our impact stays in line with the earth's carrying capacity. To design and monitor effective policy, good-quality data are indispensable. Production and consumption are two sides of the same coin, and in today's globalized world, an integrated and consistent inter-country accounting framework that links these two is a necessity for adequate analysis. A better understanding of global value chains starts with capturing production and trade relations in a coherent and complete system. More insight in the environmental impact of consumption requires an integrated environmental-economic accounting framework. Although producers generally are the ones to pay the wages, extract the resources, and emit the greenhouse gases - our productive system is in place to serve our consumer society. More awareness of the impact of consumption, at home and abroad, is needed to change our behaviour and create a sustainable economy. | |||
| Rueda-Cantuche, J.M., Rémond-Tiedrez, I., Velazquez-Afonso, A., Martins Ferreira, P., Rocchi, P., Valderas Jaramillo, J.M., Amores, A.F. and Roman, M.V. | Proc. International Input-Output Conference | The Eurostat-JRC project "Full International and Global Accounts for Research in Input-Output Analysis" (FIGARO) has produced experimental EU-Inter Country Supply, Use and Input-Output Tables for the year 2010 in line with the ESA 2010 methodology. Setting up a European Inter-country Supply, Use and Input-Output Table implies the compilation of a balanced view of international trade consistent with National Accounts data. It is therefore absolutely necessary to: (a) reconcile the trade asymmetries and provide one single trade flow for each bilateral transaction between partners; and (b) align the trade figures with National Accounts data, in order to capture, for instance, the potential environmental, social and economic effects of supply and demand shocks on the national economies via the existing global value (and supply) chains. The paper describes methodological issues raised by the construction process of the Inter-country Supply, Use and Input-Output Tables: e.g. econometric estimations of cif/fob margins; econometric estimations of missing bilateral services trade; alignment of trade statistics and national accounts data: e.g. goods sent abroad for processing, merchanting activities. | |||
| Ricciato, F., Skaliotis, M., Wirthmann, A., Giannakouris, K. and Reis, F. | Proc. Conference of the Directors General of the National Statistical Institutes (DGINS) | In this contribution we outline the concept of Trusted Smart Statistics as the natural evolution of official statistics in the new datafied world, where traditional data sources (survey and administrative data) represent a valuable but small portion of the global data stock, much thereof being held in the private sector. In order to move towards practical implementation of this vision a Reference Architecture for Trusted Smart Statistics is required, i.e., a coherent system of technical, organisational and legal means combined to provide an articulated set of trust guarantees to all involved players. In this paper we take a first step in this direction by proposing selected design principles and system components that, as of the current state of play, we believe will be part of the final design. The goal of this contribution is not to propose a ready-made fully-fledged solution, but rather build awareness about the necessary elements (technological and not) and fuel the discussion with the relevant stakeholders. | |||
| Salvati, M. and Mészáros, M. | Proc. conference on use of R in Official Statistics (uRos) | The object of this paper is to present the R package 'flagr' that is in development in Eurostat for facilitating the internal revision of the use of flags and flagging of aggregates in dissemination. The 'flagr' package provides general functions following the methodological guidelines suggested by the SDMX for the aggregate. The package provides three different functions how the individual flags can be transferred to the aggregate.The first one is the hierarchy of the SDMX flags suggested by the implementation guidelines. This method compares all flags of a given dataset and keeps the flag for the aggregate with the highest score on the SDMX hierarchy or in a personally specified order. The second method counts the occurrences of the flags in the underlying data and the flag for the aggregate will be the flag that has the highest count. The last method not only counts the frequency of a flag is represented in the dataset, but also it also it takes into account the weight of the individual values, as the contribution of the corresponding individual value to the aggregate. The flag, which has the highest summed weight, is used for the flag of the aggregate if it is above a certain threshold. | |||
| Vâju, S.C. and Mészáros, M. | Proc. Quality conference | Statistical authorities need to produce data faster in a cost effective way, to become more responsive to users' demands, while at the same time providing high quality output. One way to fulfil this is to make more use of already available data sources, and in particular administrative sources, most typically used in combination with other sources. Depending on the use of the administrative sources and the data configuration different statistical tasks must be applied. Usually it is not only one task but a sequence of different tasks that have to be applied, for example, data integration, imputation and editing or tabulation. For these tasks different methods are available and depending on the input data quality and the data configuration the same method can have limited use or produce lower quality outputs. The use of administrative data sources risks impacting negatively quality on several dimensions, in particular accuracy and comparability. Surveys and administrative sources have both particular strengths and weaknesses. Combining them may overcome these weaknesses, provided that suitable methodology and tools are used. At the same time, harmonised measures of quality for outputs that combine administrative sources with other sources (surveys) are necessary to ensure that European Union official statistics are of sufficient quality and fit for their intended use. This paper looks at the most frequent methodological challenges faced when integrating administrative sources and provides, for typical situations, preferred methods to have the best quality of statistical output. It also introduces the work of ESSnet on the Quality of Multisource Statistics (KOMUSO) to develop quality measures and guidelines related to the use of administrative sources. | |||
| Vanhoof, M., Reis, F., Ploetz, T. and Smoreda, Z. | Journal of Official Statistics, 34 (4), pp. 935-960 | Mobile phone data are an interesting new data source for official statistics. However, multiple problems and uncertainties need to be solved before these data can inform, support or even become an integral part of statistical production processes. In this article, we focus on arguably the most important problem hindering the application of mobile phone data in official statistics: Detecting home locations. We argue that current efforts to detect home locations suffer from a blind deployment of criteria to define a place of residence and from limited validation possibilities. We support our argument by analysing the performance of five home detection algorithms (HDAs) that have been applied to a large, French, Call Detailed Record (CDR) data set ( 18 million users, five months). Our results show that criteria choice in HDAs influences the detection of home locations for up to about 40% of users, that HDAs perform poorly when compared with a validation data set (resulting in 358-gap), and that their performance is sensitive to the time period and the duration of observation. Based on our findings and experiences, we offer several recommendations for official statistics. If adopted, our recommendations would help ensure more reliable use of mobile phone data vis-à-vis official statistics. | |||
| Velazquez-Afonso, A., Rocchi, P., Rueda-Cantuche, J.M. and Rémond-Tiedrez, I. | Proc. International Input-Output Conference | The extension from national to inter-country Supply, Use and Input-Output tables (SUIOTs) consists in splitting national SUTs domestic exports (FOB) by country of destination (and importing industry) and by type of use (intermediate or final), which in turn produces indirect estimations of imports of intermediate and final goods and services among countries of origin (and exported products). It could also be the other way round, splitting national SUTs imports by countries of origin, as in the WIOD approach. The two approaches should not differ, in principle, as long as the view of bilateral trade among countries is balanced at the level of each good and service and both exports and imports are valued in FOB. However, this is not the case in official statistics, mostly due to trade asymmetries and the different valuation of exports (FOB) and imports (CIF). This paper however justifies the first choice for various reasons and put a special focus on the treatment of goods sent abroad for processing, including some indications about the necessary assumptions made in the absence of official data about trading partners and type and destination of the processed goods. | |||
| Capaccioli, M., Gramaglia, L. and Pellegrino, M. | |||||
| Aaberge, R., Bourguignon, F., Brandolini, A., Ferreira, F.H.G., Gornick, J.C., Hills, J., Jäntti, M., Jenkins, S.P., Marlier, E., Micklewright, J., Nolan, B., Piketty, T., Radermacher, W.J., Smeeding, T.M., Stern, N.H., Stiglitz, J. and Sutherland, H. | Review of Income and Wealth, 63 (3), pp. 411-444 | Tony Atkinson is universally celebrated for his outstanding contributions to the measurement and analysis of inequality, but he never saw the study of inequality as a separate branch of economics. He was an economist in the classical sense, rejecting any sub‐field labelling of his interests and expertise, and he made contributions right across economics. His death on 1 January 2017 deprived the world of both an intellectual giant and a deeply committed public servant in the broadest sense of the term. This collective tribute highlights the range, depth and importance of Tony's enormous legacy, the product of almost fifty years’ work. | |||
| Aprigliano, V., Foroni, C., Marcellino, M., Mazzi, G. and Venditti, F. | International Journal of Computational Economics and Econometrics, 7 (1-2), pp. 43-63 | In this paper, we study alternative methods to construct a daily indicator of growth for the euro area. We aim for an indicator that (i) provides reliable predictions, (ii) can be easily updated at the daily frequency, (iii) gives interpretable signals, and (iv) it is linear. Using a large panel of daily and monthly data for the euro area we explore the performance of two classes of models: bridge and U-MIDAS models, and different forecast combination strategies. Forecasts obtained from U-MIDAS models, combined with the inverse MSE weights, best satisfy the required criteria. | |||
| Buono, D., Amores, A.F. and Rémond-Tiedrez, I. | Eurostat | This study aims to realize a statistical analysis of competitiveness in the EU-28 based on a statistical reference framework, previously defined as the European Wheel of Competitiveness. This framework comprises a list of 35 indicators (EWoC indicators) related to macroeconomics, microeconomics, globalization, environment and socio-institutional aspects. The analytical methods for this study were established in line with the Statistical reference framework for competitiveness analysis in the EU-28 Member States. As a rather broad concept, competitiveness can be described by a large set of different factors and definitions. The aim of this analysis is to show possible redundancy between indicators, but also possible explanatory power. Moreover, it tests the initial assumption that the largest principal components will be sufficient to explain the variability in the observed dataset. Finally, it detects possible patterns based on available set of indicators. Results confirmed some well-known correlations. For instance, the unemployment rate is positively correlated with the indicator People at risk of poverty or social exclusion (AROPE), which is also negatively correlated with the Real GDP per capita. Nevertheless, the performed correlation analysis did not provide any substantial results regarding some other expected correlations. It has to be mentioned at this point that, the presence or the absence of correlation results between several indicators of the set of EWoC indicators, is a fact that should not be understand as a weakness of the EWoC framework but rather as a strength due to the fact that there is not redundant information. Exploring the high correlations between the aforementioned indicators and indicators by themselves, it was decided to control for the indicator 4. Concerning the results obtained with partial correlation analysis, it was evident that most of the previously captured correlation actually comes from the Gross domestic expenditure on R&D. More precisely, when controlling the correlation for the aforementioned indicator, the correlation across EWoC indicators becomes weaker or insignificant in almost all cases. For that reason, and other reasons detailed in the article, indicator 4 was not used for the latter analysis. Finally, the correlation analysis showed that indicator 34: Control of corruption could be also removed from the set of the EWoC indicators. The cross-correlation analysis explored time series correlation and showed that for the same pair of indicators, different or opposite correlation results can be obtained. This proved that countries may react differently and in several periods in time, to similar economic changes. This result provided the idea of countries clustering. In addition, obtained correlation coefficients vary from country to country. Therefore, it was of interest to look for the evidence of formation of groups of countries. In another words, the country-clusters. EU-28The performed analysis showed that the "old" EU Member States (France, Germany, United Kingdom, Italy...) form a cluster while the Eastern EU countries, i.e. "newest"Member States (Estonia, Latvia, Lithuania, Poland, Bulgaria, Romania, Croatia...) form a separate cluster. It is also noteworthy the fact that Luxembourg stands out as being very different, insofar as it forms its own cluster (Figure 1). The explored dataset consists of 29 indicators for time span 2000-2014. Therefore, it seemed logic to examine opportunities for the reduction of dimensionality or indicators` grouping. All analysis (Principal Components, k-means cluster analysis and Gaussian mixture model and the Hierarchical agglomerative clustering analysis) showed that indicators, either as a component of one linear combination or as a member of one group, can be classified into 4 groups. It is noteworthy the fact that indicator 29: Real GDP per capita stands out as being different, insofar as it forms its own cluster | |||
| Buono, D., Mazzi, G.L., Kapetanios, G., Marcellino, M. and Papailias, F. | Eurostat Review on National Accounts and Macroeconomic Indicators (EURONA), 1, pp. 67-77 | In this paper we present a detailed discussion on various types of big data which can be useful in macroeconomic nowcasting. In particular, we review the big data sources, availability, specific characteristics and their use in the literature. We conclude this paper identifying the big data types which could be adopted for real applications. | |||
| Bouwmeester, M.C. and Oosterhaven, J. | Energy Policy, 106, pp. 288-297 | In this paper we use a non-linear programming approach to predict the wider interregional and interindustry impacts of natural gas flow disruptions. In the short run, economic actors attempt to continue their business-as-usual and follow established trade patters as closely as possible. In the model this is modelled by minimizing the information gain between the original pattern of economic transactions and the situation in which natural gas flows are disrupted. We analyze four scenarios that simulate Russian export stops of natural gas by means of a model calibrated on an international input-output table with six sectors and six regions. The simulations show that at the lower levels of aggregation considerable effects are found. At the aggregate level of the whole economy, however, the impacts of the four scenarios are negligible for Europe and only a little less so for Russia itself. Interestingly, the effects on the size of the economy, as measured by its GDP, are predominantly positive for the various European regions, but negative for Russia. The effects on the welfare of the populations involved, however, as measured by the size of domestic final demand, have an opposite sign; with predominantly negligible but negative effects for European regions, and very small positive effects for the Russian population. | |||
| Brandmueller, T., Schäfer, G., Ekkehard, P., Müller, O. and Angelova-Tosheva, V. | Regional Statistics, 7 (1), pp. 78-89 | Regional statistics, along with the NUTS (Nomenclature des Unités Territoriales Statistiques, or Nomenclature of Territo-rial Units for Statistics) classification, al-ready have a solid tradition. They have developed into a very useful tool for de-tailed analyses and have become the basis for important decisions in the allocation of EU funding. Gradually, the scope of regional statistics has widened, and re-gional statistics now play a role in several statistical domains with a wide range of statistical indicators. The recognition that many of the social and economic issues Europe faces today have urban or rural characteristics has led to an initiative to supplement statistical da-ta on NUTS regions with data on cities and rural areas. These sub-national statistics allow policy makers to better target their policies. For example, in some parts of Eu-rope, poverty and social exclusion are clear-ly an urban problem, while in other areas they are primarily a rural problem. A further aspect that has gained considera-ble importance in territorial policy making - as well as in public awareness - concerns the so-called functional regions, which are selected or constructed from more detailed geographical units according to specific features. The labour market area is one ex-ample of this type of functional delinea-tion, which helps to shed light on im-portant territorial characteristics. The fast-growing use of geographic in-formation and new technical facilities has created possibilities for merging statistics and related geographical information into so-called spatial statistics. An example is grid-based population data, which helps to determine the concrete locations of peo-ple with access to certain facilities (e.g. public transport, airports) or to identify a population close to the sea. Through the intensive use of map-related functions, the utility of regional and urban statistics can also be enhanced, and different statistics can be combined. This paper argues that different sub-national statistics offer different but inter-related perspectives. They can be com-bined in multiple ways to create new pos-sibilities for policy analysis and to illus-trate social and economic characteristics at varying levels of geographic detail. | |||
| Bujnowska, A. | Proc. work session on Statistical Data Confidentiality | European statistics are statistics necessary for the performance of the activities of the European Union. They help measure the progress and efficiency of the Union’s policies. The annual and multiannual statistical programmes define for which economic or social domains European statistics are necessary. European statistics are in principle produced by Eurostat on the basis of the data transmitted by statistical offices in the EU countries. Eurostat publishes figuresfor the countries of the European Union (EU), European Economic Area (EEA: EU plus Iceland, Liechtenstein, Norway) and Switzerland, and compiles EU aggregates, including also for the Euro area. The statistical offices in the EU and the EEA countries transmit the data on the basis of specific subject-matter regulations. These regulations define the variables, timeliness, quality and the necessary breakdowns of the data. In most domains the rules require that confidential data are to be sent to Eurostat alongside with non-confidential data. Confidential figures may be used for production of EU aggregates. The European Statistical System consists of all partners involved in the production of European statistics, namely: national statistical institutes (NSIs), other national authorities (ONAs, for example: regional statistical offices, ministries) and Eurostat. Statistical offices in the EU countries (NSIs and ONAs) are often referred to as national statistical authorities (NSAs). The members of the ESS cooperate to produce good quality European statistics on the basis of aligned methods, tools and processes. | |||
| Capaccioli, M. | Proc. workshop on Implementing Efficiencies and Quality of Output | The statistical organisations are facing several challenges: their mission is evolving, the budget and human resources are shrinking and new IT technologies are appearing on the market. They need to improve their rapidity to respond to new user requirements and maintain at the same time high quality products and services. In this context, managing business processes is an important sign of maturity and efficiency in organisations. Eurostat has decided to launch the project Process Management Framework (PMF) with the objective to build a harmonised documentation of the Eurostat processes, increase the process management maturity and create a pool of competence for business process modelling. This project is strongly linked with the Quality review initiative undertaken by Eurostat. | |||
| Grazzini, J. and Lamarche, P. | Proc. New Techniques and Technologies for Statistics (NTTS) | The scope of this paper is to present a practical framework adopted for the integration of software applications into a statistical production chain. The focus is the actual implementation of a high-level collaborative platform aiming not only at producing social statistics, but also at further fostering experimentation and analysis in that field. In doing so, we strongly support the (obvious) claim that "the modernisation and industrialisation of official statistical production needs a unified combination of statistics and computer science in its very principles". Motivated by the consensus that processes - in particular statistical processes - for data-driven policy should be transparent, we naturally promote open, reproducible, reusable, verifiable, and collaborative software development and deployment in a statistical organisation. Beyond just devising guidelines and best practices, we show how the platform is implemented for the production of social statistics. For that purpose, we adopt a reasonable mix of bottom-up (from low-level scope to high-level vision) and top-down (from black-box process models to traceable functional modules) designs, so as to "think global, [and] act local". In building the parts while planning the whole, we provide with a flexible and agile approach to immediate needs and current legacy issues, as well as long-term problems and potential future requirements for statistical production. | |||
| Hamadeh, N., Mouyelo-Katoula, M., Konijn, P. and Koechlin, F. | Social Indicators Research, 131 (1), pp. 23-42 | The International Comparison Program (ICP) is a worldwide statistical initiative designed to estimate purchasing power parities (PPPs) that can be used as currency converters to compare the performance of countries around the world, thereby providing in-depth views of the distribution of resources worldwide. The 2011 round of the ICP was leveraged on the successful outcome of the 2005 round that included 146 countries, introducing various methodological improvements. The summary report and results from the 2011 round were released in April 2014 and provided PPPs, price levels indices, and expenditures in PPP terms for the GDP and major aggregates for 199 participating countries. More detailed results were released in June 2014 and a final comprehensive report in October 2014. The final report provided a more in-depth analysis of volume and per capita indices. The results stirred a strong debate among the user community because of their finding that the world has become more equal than previously thought. The purpose of this paper is to provide an overview of the main results and findings of ICP 2011, its governance framework and partnership with the Eurostat-Organization for Economic Co-operation and Development (OECD) PPP program, and the major methodological innovations that were implemented. The paper reviews the major uses of the PPPs generated by the ICP 2011 and the Eurostat-OECD PPP program, and concludes with thoughts about the future of the ICP. | |||
| Hagsten, E. and Sabadash, A. | International Journal of Manpower, 38 (3), pp. 373-391 | The purpose of this paper is to broaden the perspective on how information and communication technology (ICT) relates to productivity by introducing a novel ICT variable: the share of ICT-schooled employees in firms, an intangible input often neglected or difficult to measure. | |||
| Koechlin, F., Konijn, P., Lorenzoni, L. and Schreyer, P. | Social Indicators Research, 131 (1), pp. 43-64 | Health services are among the most comparison-resistant services in international comparisons such as the Eurostat–OECD Purchasing Power Parities (PPP) program and the ICP. Traditionally, PPPs for health services are estimated on the basis of input methods, e.g. by comparing salaries of doctors and nurses. This mainly reflects the difficulties inherent in measuring the output of services produced by nonmarket producers. Since 2007, OECD and Eurostat have undertaken work, with their Member States, to develop explicit output-based measures of prices and volumes of hospital services directed at comparisons across countries. The approach is based on collecting quasi-prices for a basket of comparable and representative medical and surgical hospital services. Eurostat and OECD used the new approach for the first time in their PPP calculations that entered the 2011 ICP benchmark round. The paper describes the output-based approach, the way it was developed and tested to assess its feasibility, and the results based on the latest data collection. | |||
| Bouwmeester, M.C. and Scholtens, B. | Energy Policy, 106, pp. 288-297 | We investigate the implications of an integrated vis-à-vis a national perspective regarding investment in natural gas infrastructure. In particular, we analyze cross-border spillovers related to the investment expenditure of five Western European countries. We develop a practical approach to estimate such cross-border investment expenditure spillovers using a multi-regional input-output model. We find that international spillovers are generally larger for employment compensation compared to capital compensation and that the spillovers are unevenly distributed among the countries and the types of labor. Both high-skilled and medium-skilled labor is impacted most in the country where the investments take place, whereas low-skilled labor is mostly generated outside the EU. We argue that an integrated European gas infrastructure investment policy is to be recommended. |
|||
| Pantea, S., Biagi, F. and Sabadash, A. | Information Economics and Policy, 39, pp. 36-44 | This paper examines the short run labour substitution effects of using ICT at firm-level in the manufacturing and services sectors in seven European countries, during the period 2007–2010. The data come from a unique dataset provided by the ESSLait Project on Linking Microdata, which contains internationally comparable data based on the production statistics linked at firm level with the novel ICT usage indicators. We adopt a standard conditional labour demand model and control for unobservable time-invariant firm-specific effects. The results show that ICT use has a statistically insignificant labour substitution effect and this effect is robust across countries, sectors and measures of ICT use. Our findings suggest that increased use of ICT within firms does not reduce the numbers of workers they employ. | |||
| Proietti, T., Marczak, M. and Mazzi, G.L. | Journal of Applied Econometrics, 32 (3), pp. 683-703 | EuroMInd-D is a density estimate of monthly gross domestic product (GDP) constructed according to a bottom-up approach, pooling the density estimates of 11 GDP components, by output and expenditure type. The components' density estimates are obtained from a medium-size dynamic factor model handling mixed frequencies of observation and ragged-edged data structures. They reflect both parameter and filtering uncertainty and are obtained by implementing a bootstrap algorithm for simulating from the distribution of the maximum likelihood estimators of the model parameters, and conditional simulation filters for simulating from the predictive distribution of GDP. Both algorithms process the data sequentially as they become available in real time. The GDP density estimates for the output and expenditure approach are combined using alternative weighting schemes and evaluated with different tests based on the probability integral transform and by applying scoring rules. | |||
| Rueda-Cantuche, J.M., Amores, A.F., Beutel, J. and Rémond-Tiedrez, I. | Economic Systems Research, 30 (2), pp. 252-270 | Input-Output modellers are often faced with the task of estimating missing Use tables at basic prices and also valuation matrices of the individual countries. This paper examines a selection of estimation methods applied to the European context where the analysts are not in possession of superior data. The estimation methods are restricted to the use of automated methods that would require more than just the row and column sums of the tables (as in projections) but less than a combination of various conflicting information (as in compilation). The results are assessed against the official Supply, Use and Input-Output tables of Belgium, Germany, Italy, Netherlands, Finland, Austria and Slovakia by using matrix difference metrics. The main conclusion is that using the structures of previous years usually performs better than any other approach. | |||
| Baldacci, E., Buono, D., Kapetanios, G., Krische, S., Marcellino, M.G., Mazzi, G.L. and Papailias, F. | Eurostat | Parallel advances in IT and in the social use of Internet-related applications, provide the general public with access to a vast amount of information. The associated Big Data are potentially very useful for a variety of applications, ranging from marketing to tapering fiscal evasion. From the point of view of official statistics, the main questions is whether and to what extent Big Data are a field worth investing to expand, check and improve the data production process and which types of partnerships will have to be formed for this purpose. Nowcasting of macroeconomic indicators represents a well-identified field where Big Data has the potential to play a decisive role in the future. In this paper we present the results and main recommendations from the Eurostat-funded project "Big Data and macroeconomic nowcasting", implemented by GOPA Consultants, which benefits from the cooperation and work of the Eurostat task force on Big Data and a few external academic experts. |
|||
| Eiselt, B. | Flächennutzungsmonitoring VIII. Flächensparen – Ökosystemleistungen – Handlungsstrategien | Die LUCAS-Erhebung ist eine Stichprobenerhebung in welcher vor Ort Informationen zu Bodenbedeckung und Bodennutzung aber auch Umweltinformationen, Fotos und Bodenproben (10 % der Punkte) gesammelt werden. Diese Erhebung findet in ihrer jetzigen Form seit 2009 alle drei Jahre statt. Aus den gesammelten Daten werden verschiedene EU-weit harmonisierte Informationen abgeleitet: validierte Rohdaten, statistische Tabellen zu Bodenbedeckung und Bodennutzung sowie Indikatoren, z. B. zur Charakterisierung der Landschaft. Diese Informationen finden ihre Anwendung u. a. in den folgenden Bereichen der EU-Politik: Naturschutz, Wald, Agrarpolitik, Klimawandel und Biodiversität. Es werden Anwendungsbeispiele in einigen Politik-Bereichen vorgestellt und Ergebnisse und Grenzen der derzeitigen Erhebung diskutiert sowie Maßnahmen zur ihrer Verbesserung vorgestellt. | |||
| Fernández-Ugalde, O., Jones, A., Tóth, G., Orgiazzi, A., Panagos, P. and Eiselt, B. | Joint Research Centre of the European Commission (EUR 28038EN) | While unemployment in the EU is above 10 the job vacancy rate also remains high around 1.5%. This suggests considerable unmet demand for skills, which is in the focus of the EU employment promotion policies. This paper studies the special role that schooled ICT experts in firms - an intangible input often neglected and difficult to measure - play for productivity. The effects are investigated both in isolation and in conjunction with the impact of ICT maturity on microdata in six European countries (UK, France, Sweden, Norway, Denmark and Finland) for the period 2001-2009. We find that increases in the proportion of ICT-intensive human capital boosts productivity. This seems to confirm the case in favour of recruitment of highly skilled ICT employees. However, the gains vary across countries and industries, suggesting that the channels through which the effects operate are narrower for ICT-intensive human capital than for skilled human capital in general. Our findings provide an important message to the EU employment policy debate that currently revolves around the skill mismatch in general and the unmet demand for ICT skills in particular. | |||
| Haldorson, M., Zaccheddu, P.-G., Fohgrub, B. and Petri, E. | Statistical Journal of the IAOS, 32 (4), pp. 481-487 | The United Nations initiative on Global Geospatial Information Management (UN-GGIM) aims at playing a leading role in setting the agenda for the development of global geospatial information and to promote its use to address key global challenges like the UN Sustainable Development Goals. The regional committee UN-GGIM: Europe was established in October 2014 and by October 2015, at its second plenary meeting, recommendations were adopted on better integration of geospatial and statistical information in order to foster further usage. The recommendations can be found in a report titled ''Definition of the priority user needs for combinations of data''. This article reflects the main content of the report: identifying relevant policies, collecting use cases, describing and responding to user needs and finally making recommendations on how to improve the integration of statistical and geospatial information. The most strategic recommendation is that Europe should aim for a European Spatial Data Strategy. Other recommendations deal with priority data for a Statistical Geospatial Framework and support the improvement of workflows with geospatial technology. | |||
| Ioannidis, E., Merkouris, T., Zhang, L.-C., Karlberg, M., Petrakos, M., Reis, F. and Stavropoulos, P. | Journal of Official Statistics, 32 (2), pp. 259-286 | This article considers a modular approach to the design of integrated social surveys. The approach consists of grouping variables into ‘modules’, each of which is then allocated to one or more ‘instruments’. Each instrument is then administered to a random sample of population units, and each sample unit responds to all modules of the instrument. This approach offers a way of designing a system of integrated social surveys that balances the need to limit the cost and the need to obtain sufficient information. The allocation of the modules to instruments draws on the methodology of split questionnaire designs. The composition of the instruments, that is, how the modules are allocated to instruments, and the corresponding sample sizes are obtained as a solution to an optimisation problem. This optimisation involves minimisation of respondent burden and data collection cost, while respecting certain design constraints usually encountered in practice. These constraints may include, for example, the level of precision required and dependencies between the variables. We propose using a random search algorithm to find approximate optimal solutions to this problem. The algorithm is proved to fulfil conditions that ensure convergence to the global optimum and can also produce an efficient design for a split questionnaire. | |||
| Karlberg, M. | Statistical Journal of the IAOS, 32 (1), pp. 29-31 | Kenett and Shmueli rightly note that statisticians in academia, industry (and the public sector for that matter!) are regularly reviewing papers for journals without a general framework to help them guide the review process, meaning that "it is typically left to the reviewer's experience and good sense to determine the contribution of a paper". The inevitable consequence is indeed that the review process "is usually carriedout in an unstructured way with inherent variability between reviewers".To remedy this regrettable state of affairs, the authors propose that a set of items based on the InfoQ framework be adopted in the reviewing process of applied journals. This discussion paper which reflects on their proposal, starts by identifying possible actions complementary to a reviewing framework in Section 2. Thereafter, the applicability of the proposed framework is discussed in Section 3, while Section 4 contains some concluding remarks. | |||
| Lazar, A.C., Selenius, J. and Jortay, M. | Proc. International Conference on Agricultural Statistics | Many important policies of the European Union, such as the Common Agricultural Policy, depend on agricultural statistics. These statistics need to be of high quality, coherent, comparable and flexible, and should be produced efficiently based on users' needs in order to best serve evidence-based policy making and monitoring. The current EU agricultural statistics system does not fulfil these requirements well enough. To address this, Eurostat launched the "New legislation on Agricultural Statistics for a strategy towards 2020 and beyond" initiative in 2014. It aims to introduce two new legal frameworks stepwise: an"Integrated Farm Statistics" Regulation which will provide the basis for collecting farm level micro-data, based on a modular approach with core, module and ad hoc surveys; and a "Statistics on Agricultural Input/Output" Regulation which will provide aggregated statistics in tabular form. These frameworks will contain basic elements such as scope, precision and quality requirements and will use common definitions and classifications, while more technical elements will be covered by secondary legislation. EU Member States will be free to choose data sources, including administrative and other new data sources. This paper presents the Strategy for agricultural statistics 2020 and beyond and shows its suitability to meet technical and methodological requirements as well as to successfully navigate the complex institutional, legal and political context within the European Union and its 28 Member States. It can therefore serve as an instructive example for a cross-border implementation of the United Nations Global Strategy to improve agricultural and rural Statistics. | |||
| Rémond-Tiedrez, I., Amores, A.F. and Rueda-Cantuche, J.M. | Proc. International Input-Output Conference | The paper will introduce the methodology for the Quality Adjusted Labour Index (QALI) in the European Union which combines macro-data from National Accounts (which are the benchmarked data) and micro-data from the EU statistics of the Labour Force survey (LFS) and the Structural Earnings Survey (SES). The Quality Adjusted Labour Input is constructed for the EU-28, EA-19 and each EU MS, whenever data are available, for the full time series from 2002 to 2013, with possible extension to 2014. Survey-based data of hours worked and earnings for 2002-2007 are converted from NACE Rev.1.1to NACE Rev.2. The QALI values by EU Member State are weighted by skills, by age and by combinations of skill and age groups. The industry breakdown varies depending on countries due to reliability/confidentiality constraints of the survey data: 21 industries (A21) for some countries, EU28 and EA19; 10 industries (A10); and the total economy. Connected to the decomposition of the volume by type of workers (by age and by skill), the results will give interesting insights on what kind of employment is supported by European exports in terms of age, qualifications, and in which industrial activities. The results will be based on the European consolidated Supply, Use and Input-Output Tables produced annually by Eurostat. | |||
| Wirthmann, A. | AStA Wirtschafts- und Sozialstatistisches Archiv, 10 (2-3), pp. 151-161 | Starting with the Scheveningen Memorandum, Eurostat created an internal Task Force “Big Data” that is coordinating the activities of the European Statistical System (ESS) on Big Data. The activities are based on the Big Data Action Plan and Roadmap which was endorsed by the European Statistical System Committee in June 2014. The Action Plan identifies short, medium and long term objectives aiming at integrating big data sources into the production of European Statistics. The BIGD project makes part of the ESS Vision 2020 for modernising European Statistics. Pilots that investigate the potential of selected big data sources for European Statistics constitute the core part of the BIGD project. The pilots are conducted by a consortium of national statistical institutes, so called ESSnets, which are co-financed by the European Commission. The pilots are backed by a number of cross-cutting activities that analyse conditions of using big data by statistical institutes, such as analysis of the legal situation, ethical principles, skills and competences, and communication. The ESSnet started working in 2016, activities will terminate in 2019. The long term objective of the Big Data Action Plan and Roadmap is integrating big data into the portfolio of European Statistics. The ESS is closely collaborating with initiatives at UN level and with data for policy initiatives at the European Commission. | |||
| Agafitei, M., Gras, F., Kloek, W., Reis, F. and Vâju, S.C. | Statistical Journal of the IAOS, 31 (2), pp. 203-211 | Many statistical offices have been moving towards an increased use of administrative data sources for statistical purposes, both as a substitute and as a complement to survey data. Moreover, the emergence of big data constitutes a further increase in available sources. As a result, statistical output in official statistics is increasingly based on complex combinations of sources.The quality of such statistics depends on the quality of the primary sources and on the ways they are combined.This paper analyses the appropriateness of the current set of output quality measures for multiple source statistics, it explains the need for improvement and outlines directions for further work. The usual approach for measuring the quality of the statistical output is to assess quality through the measurement of the input and process quality. The paper argues that in multisource production environment this approach is not sufficient. It advocates measuring quality on the basis of the output itself - without analysing the details of the inputs and the production process - and proposes directions for further development. | |||
| Boxall, M., Brown, G., Buono, D., Elliott, D., Kirchner, R., Ladiray, D., Mazzi, G.L. and Ruggeri Cannata, R. | The establishment of common guidelines for seasonal adjustment (SA) within the European Statistical System (ESS) is an essential step towards a better harmonisation and comparability of infra-annual statistics, especially Principal European Economic Indicators (PEEIs). The ESS Guidelines on Seasonal Adjustment address the need for harmonisation expressed on several occasions by many users such as the European Central Bank (ECB), European Commission services, and the ECOFIN Council. The definition of best practices in the field of seasonal adjustment has been long debated at European level. Since 2007, the Seasonal Adjustment Steering Group co-chaired by Eurostat and the ECB gave a new and crucial input to the compilation of the first edition of the guidelines, published in 2009. The first edition has been widely accepted and implemented. However, taking into account the experience accumulated since 2009 and the need to further clarify some specific aspects, in 2012 the Seasonal Adjustment Steering Group decided to launch a revision of the guidelines. The ESS Guidelines on Seasonal Adjustment are the outcome of the revision work and the ESS Committee (ESSC) endorsed them in November 2014. The revised ESS Guidelines on Seasonal Adjustment present both theoretical aspects and practical implementation issues in a friendly and easy to read framework, thereby addressing both experts and non- experts in seasonal adjustment. They meet the requirement of principle 7 (Sound Methodology) of the European Statistics Code of Practice and their implementation will also be in line with principles 14 (Coherence and Comparability) and 15 (Accessibility and Clarity). The guidelines also foster the transparency of seasonal adjustment practices by encouraging the documentation of all seasonal adjustment steps and the dissemination of seasonal adjustment practices by means of the metadata template for seasonal adjustment. Finally they allow for development of expertise and capacity building. The revised version of the guidelines includes a new section with a policy for seasonal adjustment, making the revised version of the guidelines consistent with the guidelines on revisions policies. It also better describes the different steps in seasonal adjustment. Finally the specification of alternatives has been reviewed, making them more operational. |
||||
| Bautier, P., Laevaert, C. and Le Goff, B. | Statistika, 95 (4), pp. 77-78 | How to build a dissemination and communication strategy in a world where users have easy access to a deluge of data and information from various origins and where IT tools and design standards change so quickly that users behaviour and their expectations are continuously modified? The first challenge of Eurostat is clearly to know what users want: we know our different types of users but we have to identify how they get our data, what they do with our data, how they react to our outputs and which sort of new service they would like us to propose. Translating these needs into a visual dissemination is a new challenge undertaken by Eurostat through a new portal, new mobile apps and new info graphs and basic application as well as increasing the visibility on Google. The objective of this paper is to share Eurostat's experience in identifying user needs and to show how concretely this information has been visually disseminated. | |||
| Götzfried, A. | Data Science, Learning by Latent Structures, and Knowledge Discovery, pp. 3-11 | In Europe, national statistical organisations and Eurostat, the statistical office of the European Union, produce and disseminate official statistics. These organisations come together as partners in the European Statistical System (ESS). This paper describes the ESS, the challenges it faces and the modernisation efforts that have been undertaken based on a redesigned ESS enterprise architecture. It also outlines the probable future direction of the ESS. | |||
| Grassi, S., Proietti, T., Frale, C., Marcellino, M. and Mazzi, G.L. | International Journal of Forecasting, 31 (3), pp. 712-738 | This paper deals with the estimation of monthly indicators of economic activity for the Euro area and its largest member countries that possess the following attributes: relevance, representativeness and timeliness. Relevance is determined by comparing our monthly indicators to the gross domestic product at chained volumes, as the most important measure of the level of economic activity. Representativeness is achieved by considering a very large number of (timely) time series of monthly indicators relating to the level of economic activity, providing a more or less complete coverage. The indicators are modelled using a large-scale parametric factor model. We discuss its specification and provide details of the statistical treatment. Computational efficiency is crucial for the estimation of large-scale parametric factor models of the dimension used in our application (considering about 170 series). To achieve it, we apply state-of-the-art state space methods that can handle temporal aggregation, and any pattern of missing values. | |||
| Infante, E., Buono, D. and Buono, A. | Eurostat Review on National Accounts and Macroeconomic Indicators (EURONA), 1, pp. 93-145 | In this paper we propose a new a priori test to be used for the identification of a common seasonal pattern. The test is applied a priori to any running of a seasonal adjustment procedure. The test is a three way ANOVA, where the three factors are the series, the time frequency and the year. One of the possible applications of using such a test would be when selecting either the direct or indirect approach when seasonally adjusting. The Seasonally Adjusted series of an aggregate can be obtained by seasonal adjusting it (direct approach) or by aggregating the seasonally adjusted individual series (indirect approach). It should be noted that, to date, the literature has been mainly focusing on an a posteriori comparison among the results achieved by applying different approaches. This paper seeks to set out an a priori strategy for the identification of the most effective seasonal adjustment of the aggregate. | |||
| Karlberg, M., Reis, F., Calizzani, C. and Gras, F. | Statistical Journal of the IAOS, 31 (3), pp. 447-462 | This paper presents key methodological results from a project on streamlining and integrating sample survey programmes. More specifically, it: Proposes a general modular framework and integrated survey systems (in concrete terms, i.e. with a specific set of surveys as the point of departure); Presents a toolbox (covering estimation, sample allocation and instrument composition) to deal with the methodological challenges associated with such integrated systems; and Indicates possible steps to upgrade statistical production systems from a collection of uncoordinated surveys to a harmonised integrated system of surveys. A concrete application of the 'instrument composition' part of the toolbox demonstrates how the EU Labour Force Survey, the EU Survey on Income and Living Conditions and the EU Adult Education Survey could be combined so as to improve flexibility (responding to new user needs), efficiency (greater precision or reduced costs) and transversality (capacity to combine variables from different statistical domains). | |||
| Radermacher, W.J. | Review of Income and Wealth, 61 (1), pp. 18-24 | Progress of societies? Well-being of citizens? Trans-generational impact of policies? To answer such fundamental questions and much more, the European Commission published, in August 2009, its Communication on "GDP and Beyond: Measuring Progress in a Changing World." Through a co-operative project, co-chaired by Eurostat and INSEE (France), the ESS acted decisively and established an action plan to be carried out by 2020 in the context of the European Statistical Programme. This plan which also builds on Eurostat's work on Sustainable Development Indicators. For most of these actions, work has either been accomplished or is in good progress. Further challenges lie ahead, including reconciling macro- and micro-data sources on household economic resources and completing the indicators set on Quality-of-Life. The work will also contribute to the global efforts on the Sustainable Development Goals/post-2015 development agenda. | |||
| Ruggeri Cannata, R., Buono, D. and Biscosi, F. | Eurostat Review on National Accounts and Macroeconomic Indicators (EURONA), 2, pp. 97-118 | The Macroeconomic Imbalance Procedure (MIP) is a surveillance mechanism that aims to identify potential risks early on, prevent the emergence of harmful macroeconomic imbalances and correct the imbalances that are already in place. It is a system for monitoring economic policies and detecting potential harms to the proper functioning of the economy of a Member State, of the Economic and Monetary Union, and of the European Union as a whole. The MIP is supported by the analysis of a set of headline and auxiliary indicators, whose data coverage can reach twenty years due to data transformations. In order to ensure the necessary time series length for policy makers, statisticians can resort to statistical techniques such as back-calculation. This paper illustrates the MIP in the European Union policy context and some applications of back-calculation to two MIP indicators. | |||
| Chiappero-Martinetti, E. and Sabadash, A. | The Capability Approach: From Theory to Practice, pp. 206-230 | The aim of this chapter is to investigate the possibility of combining human capital theory (HCT) and the capability approach (CA) in order to better understand and measure both the instrumental and the intrinsic values of education for individuals, and to trace its relative spillover effects on societies. HCT, pioneered by Schultz and Becker in the early 1970s, has since become an important part of the debate on economic growth and development. Recently, HCT has been criticised for the narrow instrumental role that it assigns to education (inasmuch as HCT disregards some of important non-material aspects of education), as well as for its inability to satisfactorily reflect the cultural, gender-based, emotional and historical differences that can influence educational choices and individual well-being. | |||
| Hagsten, E. and Sabadash, A. | Joint Research Centre of the European Commission (JRC89703) | While unemployment in the EU is above 10 the job vacancy rate also remains high around 1.5%. This suggests considerable unmet demand for skills, which is in the focus of the EU employment promotion policies. This paper studies the special role that schooled ICT experts in firms - an intangible input often neglected and difficult to measure - play for productivity. The effects are investigated both in isolation and in conjunction with the impact of ICT maturity on microdata in six European countries (UK, France, Sweden, Norway, Denmark and Finland) for the period 2001-2009. We find that increases in the proportion of ICT-intensive human capital boosts productivity. This seems to confirm the case in favour of recruitment of highly skilled ICT employees. However, the gains vary across countries and industries, suggesting that the channels through which the effects operate are narrower for ICT-intensive human capital than for skilled human capital in general. Our findings provide an important message to the EU employment policy debate that currently revolves around the skill mismatch in general and the unmet demand for ICT skills in particular. | |||
| Mazzi, G.L., Mitchell, J. and Montana, G. | Oxford Bulletin Of Economics And Statistics, 76 (2), pp. 233-256 | Combined density nowcasts for quarterly Euro‐area GDP growth are produced based on the real‐time performance of component models. Components are distinguished by their use of ‘hard’ and ‘soft’, aggregate and disaggregate, indicators. We consider the accuracy of the density nowcasts as within‐quarter indicator data accumulate. We find that the relative utility of ‘soft’ indicators surged during the recession. But as this instability was hard to detect in real‐time it helps, when producing density nowcasts unknowing any within‐quarter ‘hard’ data, to weight the different indicators equally. On receipt of ‘hard’ data for the second month in the quarter better calibrated densities are obtained by giving a higher weight in the combination to ‘hard’ indicators. | |||
| Pantea, S., Biagi, F. and Sabadash, A. | Joint Research Centre of the European Commission (JRC9112) | This paper examines whether ICT substitute labour and reduce the demand for labour. We used firm-level comparable data separately for firms in manufacturing, services and ICT-producing sectors from seven European countries. We adopted a common methodology and applied it to a unique dataset provided by the ESSLait Project on Linking Microdata. We controlled for unobservable time-invariant firm-specific effects and we found no evidence of a negative relationship between intensity of ICT use and employment growth. We read this as an indication that ICT use is not reducing employment among ICT using firms. | |||
| Sabadash, A. | Joint Research Centre of the European Commission (JRC92503) | This study examines the evolution of the number of ICT-skilled workers employed in industry sectors in the EU28 over the period 2000-2012. Data are taken from the Eurostat Labour Force Statistics. It introduces a novel definition of ICT specialists that combines occupations and skills taxonomies. For the period prior to the introduction of the Standard Classification of Occupations (ISCO-08) it starts from the OECD definition but includes a wider range of ICT occupations. From 2011 onwards it adopts the thematic view for ICT occupations proposed by the ILO (2012). It confirms that employment of ICT specialists in the EU27 has been resilient to the economic downturn and uncertainty in global labour markets, and was able to maintain a growth path of 4.3% per year over the period 2000-2012, more than 7 times higher than average growth of total employment over the same period. Though ICT employment evolved cyclically it never turned negative. This rapid growth in ICT employment confirms the increasing importance of ICT technologies in the global economy. | |||
| Billio, M., Ferrara, L., Guégan, D. and Mazzi, G.L. | Journal of Forecasting, 32 (7), pp. 577-586 | In this paper, we aim at assessing Markov switching and threshold models in their ability to identify turning points of economic cycles. By using vintage data updated on a monthly basis, we compare their ability to date ex post the occurrence of turning points, evaluate the stability over time of the signal emitted by the models and assess their ability to detect in real-time recession signals. We show that the competitive use of these models provides a more robust analysis and detection of turning points. To perform the complete analysis, we have built a historical vintage database for the euro area going back to 1970 for two monthly macroeconomic variables of major importance for short-term economic outlook, namely the industrial production index and the unemployment rate. | |||
| De Smedt, M. | Social Indicators Research, 114 (1), pp. 153-167 | Over the last decades, the European Statistical System has developed many European statistics and indicators to measure social progress and sustainable development. Initially only in a few cases the measuring instruments contained questions on subjective issues. With the adoption of its Communication on "gross domestic product and beyond" the Commission has given an impetus to the development of subjective social indicators. This has led to the establishment of a first set of indicators on quality of life and well-being and to a new instrument (the 2013 EU-SILC ad-hoc module for measuring subjective well-being). This new step in European statistics creates an important potential for researchers to engage in in-depth analysis and for national and European Union policy makers to use the resulting indicators-and in casu subjective well-being indicators-for developing and monitoring policy strategies and programmes. | |||
| Defays, D. and Museux, J.-M. | Journal of Official Statistics, 29 (1), pp. 147-155 | This discussion draws mainly on four contributions in this special issue (those of Statistics New Zealand, NASS, RTI International and Statistics Netherlands) that report on experiences in integrating statistical production systems with a direct focus on industrialisation and integration-related issues. The framework proposed by Eltinge et al. for the integration of architecture and methodology is also taken on board. The article on the Real-Time Online Analytic System (Westat/NCHS) is marginally integrated into the discussion on data access. | |||
| Infante, E. and Buono, D. | Proc. New Techniques and Technologies for Statistics (NTTS) | Market price data plays an essential role when aiming at the production of quality statistics to be used by policy makers at EU level. Market risk can be defined as the risk of losses in positions arising from movements in market prices, generally linked to the risk that commodity prices and/or their implied volatility will change. From the analyst's perspective, the most informative data are possibly located within the end-series observations. This paper proposes a new Technique for Statistics to be used for assessing the presence of commodity risk that might cause market risk. The underlining idea is to assess whether the realized prices for a determined product in a specified time span is significantly apart from the SARIMA forecasts intervals. Such procedure aims also at identifying the type of eventual outliers present within the end-series observations. An applied case study on agricultural price statistics in Italy is here presented. | |||
| Infante, E., Buono, D. and Buono, A. | Proc. New Techniques and Technologies for Statistics (NTTS) | The seasonally adjusted series of an aggregate can be obtained by seasonal adjusting it ("direct approach") or by aggregating the seasonally adjusted individual series ("indirect approach"). The literature to date has mainly focused upon an a posteriori comparison among the results achieved by applying different approaches. Here a new a priori test (IB test) for choosing between direct and indirect approach in seasonal adjustment is proposed. The test is applied before running any seasonal adjustment procedure. When the individual series present common seasonal patterns the aggregate will be adjusted directly, otherwise an indirect approach could be preferred. Sections 3 and 4 include a simulation and a case study, respectively. This paper seeks to set out an a priori strategy for the identification of the most effective seasonal adjustment approach to be used. | |||
| Tukker, A., De Koning, A., Wood, R., Moll, S. and Bouwmeester, M.C. | Environmental Science and Technology, 47 (4), pp. 1775-1783 | Environmentally extended input output (EE IO) analysis is increasingly used to assess the carbon footprint of final consumption. Official EE IO data are, however, at best available for single countries or regions such as the EU27. This causes problems in assessing pollution embodied in imported products. The popular “domestic technology assumption (DTA)” leads to errors. Improved approaches based on Life Cycle Inventory data, Multiregional EE IO tables, etc. rely on unofficial research data and modeling, making them difficult to implement by statistical offices. The DTA can lead to errors for three main reasons: exporting countries can have higher impact intensities; may use more intermediate inputs for the same output; or may sell the imported products for lower/other prices than those produced domestically. The last factor is relevant for sustainable consumption policies of importing countries, whereas the first factors are mainly a matter of making production in exporting countries more eco-efficient. We elaborated a simple correction for price differences in imports and domestic production using monetary and physical data from official import and export statistics. A case study for the EU27 shows that this “price-adjusted DTA” gives a partial but meaningful adjustment of pollution embodied in trade compared to multiregional EE IO studies. | |||
| Madans, J., Abou-Zahr, C., Bercovich, A., Boerma, T., Carlton, D., Castro, L., De Smedt, M., Domingo, E., Kahimbaara, J., Marquardt, M., Nviiri, H., Norgaard, E., Vassenden, E. and Wolfson, M. | Statistical Journal of the IAOS, 28 (1-2), pp. 3-11 | The field of health statistics has lagged behind other areas of statistics particularly in relation to reliable, timely, core information on health for use within countries and for cross national comparisons. A new framework is needed to successfully reshape health statistics. The UN Statistical Commission at its 35th meeting (2004) called for the establishment of an "inter-secretariat working group on health statistics (ISWG-HS) to develop a coordinated and integrated agenda for the production of health statistics and agree on standard definitions, classifications and methodologies in health statistics taking advantage of existing mechanisms wherever possible, and involving the community of official statistics at all stages." The Framework for health statistics described in this paper was developed by the members of this group. The Framework for Health Statistics provides a structure for identifying the kinds of information that should be collected; for assessing the extent to which these data are available and with what quality and comparability; for identifying data gaps; and for identifying where international standards are needed to support the collection of high-quality information. It facilitates dialogue among the national statistical authorities and other parties that fund or conduct health data collection, including health ministries and other para-statistical organizations such as institutes for public health. | |||
| Frale, C., Marcellino, M., Mazzi, G.L. and Proietti, T. | Journal of Forecasting, 29 (1-2), pp. 109-131 | In this paper we propose a monthly measure for the euro area gross domestic product (GDP) based on a small-scale factor model for mixed-frequency data, featuring two factors: the first is driven by hard data, whereas the second captures the contribution of survey variables as coincident indicators. Within this framework we evaluate both the in-sample contribution of the second survey-based factor, and the short-term forecasting performance of the model in a pseudo-real-time experiment. We find that the survey-based factor plays a significant role for two components of GDP: industrial value added and exports. Moreover, the two-factor model outperforms in terms of out-of-sample forecasting accuracy the traditional autoregressive distributed lags (ADL) specifications and the single-factor model, with few exceptions. |
|||
| Lemoine, M., Mazzi, G.L., Monperrus-Veroni, P. and Reynes, F. | Journal of Forecasting, 29 (1-2), pp. 29-53 | We develop a new version of the production function (PF) approach for estimating the output gap of the euro area. Assuming a CES (constant elasticity of substitution) technology, our model does not call for any (often imprecise) measure of the capital stock and improves the estimation of the trend total factor productivity using a multivariate unobserved components model. With real-time data, we assess this approach by comparing it with the Hodrick- Prescott (HP) filter and with a Cobb-Douglas PF approach with common cycle and implemented with a multivariate unobserved components model. Our new PF estimate appears highly concordant with the reference chronology of turning points and has better real-time properties than the univariate HP filter for sufficiently long time horizons. Its inflation forecasting power appears, like the other multivariate approach, less favourable than the statistical univariate method. |
|||
| Reuter, W. and Museux, J.-M. | Proc. International Conference on Privacy in Statistical Databases, 6344, pp. 249-257 | Eurostat is pursuing the establishment of an infrastructure for remote access for researchers in order to satisfy the growing demand for microdata. Some European countries already implemented such solutions. This paper compares the systems which can be categorized in (1) terminal server, (2) distance network and (3) job submission systems. They differ in IT infrastructure, workstation control, user management and authentication, file systems and disclosure control activities. The second part of the paper describes the efforts and outlook as well as options and challenges for Eurostat when building such a system. | |||
| Bujnowska, A. and Museux, J.-M. | Statistical Journal of the IAOS, 26 (3-4), pp. 89-94 | This paper outlines microdata access methods at the European level, and specifically to data governed by European Union (EU) Regulation 831/2002 or where explicit approval of the EU Members is given on the access to particular datasets via Eurostat safe centre. Access to EU microdata for research purposes was enabled in 2002 when the Commission Regulation (EC) No 831/2002 came into force. Since then more than 100 contracts have been signed each year with research organisations for the provision of microdata for scientific purposes. The current Regulation foresees two ways of access to microdata: access to anonymised microdata files, and access to confidential data in the safe centre in Eurostat premises in Luxembourg. The first part of the paper outlines the legal framework at the EU level. The second part discusses the different modes and conditions of access as well as practical issues related to access to microdata in general. The final part provides an overview of the projects currently carried out in the domain of remote access at the European level. The situation with regards to the access to EU microdata will evolve in the near future with the new regulatory framework and subsequent changes in the governance structure for statistical confidentiality in the European Statistical System. | |||
| Díaz Mu unoz, P. | Statistical Journal of the IAOS, 25 (1-2), pp. 47-54 | The attention given by statistical organisations to Statistical Data and Metadata Exchange (SDMX) is currently at unprecedented levels. This paper analyses the reasons for this and describes the key elements of this infrastructure. Furthermore, it describes all the dimensions of the SDMX initiative, namely, the standards, the exchange of data in different modes and the opportunity for the sharing of tools; and it links all these dimensions to the corresponding infrastructure elements. The paper also summarises the governance aspects of the initiative and outlines the benefits of adopting SDMX in an organisation, including the use of the data model in the statistical productions chain and to profit from the available components. Finally, a reflection on the global implementation of SDMX, as recommended by the United Nations Statistical Commission in February 2008, is provided in this paper. Finally, the paper urges national and international statistical organisations in the world to implement SDMX standards and guidelines and to use them in their exchanges of data; to participate in the governance mechanisms; and to act as a relay for promoting the use of SDMX by other partners. | |||
| Museux, J.-M., Peeters, M. and Jo ao Santos, M. | Proc. International Conference on Privacy in Statistical Databases, 5262, pp. 324-334 | The paper discusses the challenges linked to the need of the research community to have access to microdata files for scientific purposes. These needs have to be adequately balanced with the legal requirement of preserving the confidentiality of respondents. The paper presents the policies and instruments available at the European Union to progress in the supply of data to the research community, while respecting the legal requirements. More specifically, the paper explains the current process dealing with research projects and the work of the European Statistical System Network (ESSnet) project for statistical disclosure control. Finally the paper describes future trends that are currently investigated in the European Union, and more specifically the development of remote access facilities, the enhancement of disclosure control tools and the convergence towards common policies in Member States. | |||
| Kunzler, U. | Statistical Journal of the United Nations Economic Commission for Europe, 19 (3), pp. 119-130 | We are living in a fast changing world, especially in the ICT (Information and Communication Technologies) sector. In this difficult environment people like to use buzzwords and acronyms - in the title of this paper you find some of them used a lot in the statistical context. It is no problem to add more: CASI, CSAQ, EDI, XML, XBRL - all of them and many more will appear in this article (and in the glossary). It is not always easy for statisticians and ICT specialists to understand each other. However, ICT is needed to automate statistical data reporting in order to save resources and improve processes -- so both communities are condemned to co-operate. In this scenario, a third area with yet another jargon is playing an important role, namely e-business: more and more, statistical EDR is using e-business tools and methods, like for example EDIFACT or ebXML. This paper tries to shed some light on the ICT and e-business aspects of statistical data reporting. The questions addressed in this paper include: What is EDR? What is metadata for EDR? Which metadata standards for EDR are available or coming up? And how is the ESS concerned or involved? The current situation of EDI standardisation is examined in more detail: the transition from EDIFACT to XML and the adoption of ebXML for the ESS. | |||
| Mikkelsen, L. and Montgomery, R. | Statistical Journal of the United Nations Economic Commission for Europe, 19 (1-2), pp. 1-3 | The papers which make up the first issue of the 2002 Statistical Journal were all presented and discussed at a joint ECE/Eurostat expert meeting hosted by Statistics Canada in Ottawa, 1–4 October 2001. They are but a sub-selection of the 32 papers discussed during the 6 sessions of the meeting. | |||
| Caridi, P. and Passerini, P. | Review of Income and Wealth, 47 (2), pp. 239-250 | Recent estimates of the size of the "underground economy" have used the so-called "demand for currency approach." One of the assumptions made by these studies is that official statistics do not take into account the underground economy when estimating GDP. After setting some definitions, the paper presents a brief critical review of the method and results obtained for the European Union using this approach. It points out that the different concepts of unreported and unrecorded activities are incorrectly considered to be equivalent. The third section, after a review of the method of estimating the underground economy using the discrepancy approach, presents the new results of the authors which give an indication of the amount of the unreported activities already included in official national accounts statistics in the EU. The results of the discrepancy approach disprove the widespread belief that official statistics only include officially recorded transactions and reinforce the critical view on the results obtained with the currency-demand approach. | |||
| Mercy, J.L. and Sonnberger, H. | Proc. International Conference on Data Warehousing and Knowledge Discovery, 1874, pp. 134-145 | This paper discusses: (1) the challenges that the European Statistical System (ESS) faces as the result of the recent appearance of phenomena such as the information society and the new economy, and (2) the extent to which new technological developments in data warehousing, knowledge discovery and extensive use of the internet can contribute to successfully meeting these challenges. Two specific issues are considered: the network nature of the ESS, and the new ways of producing statistics that reinforce the needs for research applied to statistics in domains such as data integration, distributed databases, EDI, automated data capture, analytical tools and dissemination. A historical overview is given of research activities financed by the European Commission as well as their relevance for DaWaK2000. A primary goal of this paper is to provide information about relevant research within the European Statistical System, and to invite the scientific community to participate actively in upcoming calls for proposals and calls for tender financed under the IST programme to solve the urgent needs for timely and high-quality statistics. | |||
| Planas, C. | Journal of Forecasting, 17 (7), pp. 515-526 | Seasonal adjustment is performed in some data-producing agencies according to the ARIMA-model-based signal extraction theory. A stochastic linear process parametrized in terms of an ARIMA model is first fitted to the series, and from this model the models for the trend, cycle, seasonal, and irregular component can be derived. A spectrum is associated to every component model and is used to compute the optimal Wiener-Kolmogorov filter. Since the modelling is linear, prior linearization of the series with intervention techniques is performed. This paper discusses the performance of linear signal extraction with intervention techniques in non-linear processes. In particular, the following issues are discussed: (1) the ability of intervention techniques to linearize time series which present non-linearities; (2) the stability of the linear projection giving the components estimators under non-linear misspecifications; (3) the capacity of the WK filter to preserve the linearity in some components and the non-linearities in others. | |||
| Albert, J. and Amor, P. | Statistical Journal of the United Nations Economic Commission for Europe, 13 (1), pp. 31-40 | The article discusses the new project orientation of the statistical cooperation provided by Eurostat to countries in Central and Eastern Europe. In particular, the criteria used for selecting projects, as well as some of the pilot projects themselves, are described. |