Data equity and official statistics in the age of private sector data proliferation

1.1 Introduction

Over the last few years, the private sector has become a primary generator of data due to widespread digitisation of the economy and society, the use of social media platforms, and advancements of technologies like the Internet of Things and AI. Unlike traditional sources, these new data streams often offer real-time information and unique insights into people's behaviour, social dynamics, and economic trends. However, the proprietary nature of most private sector data presents challenges for public access, transparency, and governance that have led to fragmented, often conflicting, data governance arrangements worldwide. This lack of coherence can exacerbate inequalities, limit data access, and restrict data's utility as a global asset.

Within this context, data equity has emerged as one of the key principles at the basis of any proposal of new data governance framework. The term “data equity” refers to the fair and inclusive access, use, and distribution of data so that it benefits all sections of society, regardless of socioeconomic status, race, or geographic location. It involves making sure that the collection, processing, and use of data does not disproportionately benefit or harm any particular group and seeks to address disparities in data access and quality that can perpetuate social and economic inequalities. This is important because data systems significantly influence access to resources and opportunities in society. In this sense, data equity aims to correct imbalances that have historically affected various groups and to ensure that decision-making based on data does not perpetuate these inequities.

1.2 The world economic forum insights on the multiple dimensions of data equity

The advent of data-driven technologies and the rise of big data have shifted the balance of data ownership significantly towards private companies. Corporations, especially those in technology and finance, possess vast quantities of data on individual behaviour, purchasing habits, and online activity, far surpassing the data traditionally gathered by governments. This shift has prompted discussions on data equity on a global scale, with the World Economic Forum among the key institutions emphasising the need for equitable data governance.

The WEF's recent reports and white papers on data equity and digital transformation ¹ , such as the “Data for Common Purpose Initiative” (DCPI), have underscored how data ownership and access impact equitable outcomes. For instance, the DCPI promotes frameworks that would enable data sharing in ways that align with the public interest. The WEF argues that in order to bridge gaps in data access and ensure that marginalised groups are not excluded from data-driven decision-making, it is essential to establish clear rules on data ownership, portability, and sharing. This focus on equitable data governance highlights how private sector data, if accessible and responsibly shared, could contribute to social good by informing policy, supporting public health initiatives, and addressing inequalities.

The WEF's work has thus helped place data equity on the agenda by demonstrating the potential risks of data concentration and by advocating for mechanisms that allow data to be shared across sectors in ways that benefit all. According to the WEF, data is not simply an economic asset but a societal one, warranting policies and practices that prioritise equity, trust, and accountability. This emphasis on data as a societal asset frames data equity as a public good that must be regulated and managed to avoid exacerbating existing inequalities. The World Economic Forum's document “Advancing Data Equity: An Action-Oriented Framework” discusses how the principles of data equity can be embedded across various sectors, emphasising fair data practices that protect human rights and ensure inclusive outcomes. It provides a comprehensive approach for addressing imbalances in how data is used and shared, especially as technology and automated decision-making processes become more integral to everyday life. The document outlines key areas where equity can be implemented throughout the data lifecycle:

Input Data Equity: This stage involves equitable data collection, ensuring that the data gathered reflects the diversity of the population. It also addresses issues of historical bias, ensuring that data from marginalised groups are included.

1.3 Statisticians’ and economists’ views on data equity

While both statisticians and economists agree on the importance of data equity, traditionally they tend to approach it from different angles due to their distinct disciplinary focuses.

Statisticians prioritise issues related to the quality, integrity and accessibility of data. For statisticians, data equity is mainly about ensuring that data is accurate, unbiased, and representative of the population. They emphasise the technical aspects of data collection and analysis, such as the need to avoid sampling biases that could lead to unequal representation of certain groups. This perspective is fully reflected in the Fundamental Principles of Official Statistics, which include guidelines on impartiality, quality, and transparency in data production. These principles underscore the need for national statistical offices to produce data that is objective, accessible, and reliable for all users.

Economists, on the other hand, approach data equity from the perspective of economic impact. They are concerned about how data ownership, data access, and data-driven decision-making affect economic power and resource allocation. For economists, data equity is closely linked to concepts of fair competition, market transparency, and equitable economic growth. They often advocate for policies that prevent data monopolies and ensure competitive markets, highlighting that unequal access to data can exacerbate income inequalities and reduce economic mobility. They also focus on the economic value of data, arguing that open data policies can unlock innovations, improve market efficiency, and create new opportunities for marginalised communities.

The distinction between these perspectives has significant implications for data equity policies. Statisticians’ focus on data quality and representativeness highlights the need for rigorous standards in data collection, processing, and dissemination. Economists’ emphasis on data accessibility and economic impact, meanwhile, underscores the importance of creating systems that make data widely available. Together, these perspectives contribute to a comprehensive approach to data equity that addresses both technical and social aspects.

1.4 Fundamental principles of official statistics and data equity

As we have seen, the statisticians’ perspective on data equity is fully reflected in the UN Fundamental Principles of Official Statistics (FPOS). Adopted by the UN Statistical Commission in 1994 and subsequently at the highest political level by the UN General Assembly in 2014, the FPOS have so far stood the test of time. Despite being reviewed by the Commission in two occasions, the Fundamental Principles were judged still relevant and in no need for a revision. The FPOS still serve as a strong foundation for official statistics production worldwide as they emphasise the need for impartiality, accountability, and quality, ensuring that statistical systems operate transparently and produce data that serves the public interest. In this regard, the Fundamental Principles have close connections with several of the key dimensions of data equity highlighted by the WEF documents, even if they are not concerned with data equity per sé. The WEF framework expands on the FPOS by focusing explicitly on equitable outcomes, inclusivity, and ethical governance.

It is thus possible to identify key gaps in the FPOS in terms of:

Equitable Representation. The Principles emphasize that statistics should be produced impartially ad following the highest professional standards, but they don’t explicitly cover diverse demographic representation. The goal is to ensure general accuracy and relevance across population data, but not necessarily to capture underrepresented or marginalized groups.

1.5 Recent UN initiatives combining the two perspectives

As we have seen, data equity is essential for creating a fair and inclusive society where data is used to benefit all individuals. The World Economic Forum's work has helped highlight data equity issues in a comprehensive way, advocating for data-sharing frameworks that promote public good. These documents broaden the UN Fundamental Principles of Official Statistics, which offer a set of values that can guide the professional production of equitable official statistics. While economists focus on preventing inequalities and monopolistic practices in data markets, statisticians stress the importance of producing data that are representative of all population groups and can guide policy decisions equitably. By combining these perspectives, a holistic approach to data equity can emerge, ensuring that data governance frameworks both uphold the integrity of public data and promote economic fairness.

Recently the UN has undertaken a couple of initiatives that can help combine the statisticians’ and economists’ perspectives on data equity. An important example in this direction is the paper titled “International Data Governance – Pathways to Progress” ² , which was endorsed at the 45^th session of the UN High-Level Committee on Programmes (HLCP) in 2023 and subsequently by the UN System Chief Executives Board for Coordination (CEB). This document articulates a vision and outlines steps for promoting and safeguarding data through a multistakeholder approach to international data governance, aimed at responsibly harnessing the full potential of data for the benefit of global public goods. More recently, this month, the CEB has also endorsed the document titled “Proposed Normative Foundations for International Data Governance: Goals and Principles" ³ , which suggests a set of common goals and principles that could form the normative basis for international data governance. Central to the document are three overarching goals: value, trust, and equity. In particular, data equity is promoted by empowering individuals and communities exercise control over their personal data and ensuring that the benefits of data access are distributed fairly, particularly to vulnerable and marginalized groups.

The other initiative was undertaken at the Summit of the Future last September, where the United Nations members adopted a Global Digital Compact ⁴ which aims to enable all countries to benefit from the digital transition. The Global Digital Compact sets out the objectives, principles, commitments, and actions to develop an open, free, and secure digital future for all, underlying the benefits that the digital technologies bring to humanity. In a landscape where private data sources are predominant, governments need to establish partnerships with private companies to obtain data that meets these standards and expands coverage, especially in areas where public sector data is limited. Among the initiatives related to AI, an independent International Scientific Panel on AI has been established, and a Global Dialogue on AI Governance has been initiated involving governments and all relevant stakeholders.

These initiatives provide a novel contribution to the body of recent discussions on data equity and international data governance, triggered by the rapid evolution of the digital ecosystem and the proliferation of private sector data.

2.1 Understanding the informal economy and informal employment – the statistical challenge

In this Special Issue of the Statistics Journal of the IAOS, the focus is on the measurement of informal employment, that is, the methodological standards as well as the best practices used at international level for identifying the forms of employment where workers lack formal contractual and social protections. In their Guest Editorial, Kieran Walsh and Michael Frosch provide an introduction to this rich section, which comprises eleven articles covering different aspects of informality.

The section is opened by “Revealing the unseen -The 21^st ICLS statistical standards on the informal economy”, authored by Michael Frosch (ILO). The paper provides an overview of how international statistical standards have evolved over the past 30 years, enabling an increasingly more accurate measurement of the core concepts of the informal sector and informal employment. Due to the changes in statistical labour standards during the 19^th and 20^th ICLS, as well as to the expanded experience of countries in measuring informality, a strong need emerged to revise these standards and provide a more coherent statistical framework that better explains the meaning of informality and can contribute to clarifying historical debates around how informality should be statistically defined and measured. By introducing the underlying concept of informal productive activities and defining for the first time the overarching concepts of informal economy and informal market economy, the 21^st ICLS resolution introduces a new framework aligned to the latest statistical labour standards. Key changes comprise the inclusion of agricultural activities, the recognition of dependent contractors, strengthening the definitions of informal employment and informal sector, broadening the understanding of informal work, and enhancing the relevance of the standards in high-income countries through the concept of “formal jobs with partly informal activities”. The 21st ICLS resolution is an important step forward in relation to the collection and production of statistics on the informal economy. The resolution will contribute to strengthening countries capacity to provide policy relevant statistics in a more harmonised way, thereby increasing the evidence base needed for addressing and formalising the informal sector.

The second paper, “A Data User's Perspective on the New Statistical Standards on Informality: Statistical Demands and Challenges in WIEGO's Work,” is from Gayatri Koolwal, Françoise Carré, and Joann Vanek (all from WIEGO Statistics Programme). This paper presents a data user's perspective on how recent changes in statistical standards have successfully addressed challenges to improving statistics on workers in informal employment. The findings are based on recent work of the “Statistics Programme of Women in Informal Employment: Globalizing and Organizing (WIEGO)”, using data from several national labour force surveys. The paper focuses on the measurement challenges linked to identifying key groups of informal workers, alongside related developments in international statistical standards, including improvements in the classification and identification of dependent contractors and contributing family workers through the new International Classification of Status in Employment (ICSE-18). The importance of a well-defined cross-cutting variable on place of work in identifying street vendors, market traders, home-based workers, and domestic workers is also discussed. Lastly, the paper highlights the need to measure emerging forms of non-standard employment in high income countries.

In “Presenting the informal economy in the macroeconomic accounts” by Jonathan Gessendorfer (from UNECE), Kossi Edem Kludza, and Herman Smith (both from UNDESA), the authors highlight the importance of including the informal economy in macroeconomic accounting to provide an exhaustive evaluation of the size of the economy and better measure economic well-being, particularly with the rise of informal activities driven by digitalization. Accurate macroeconomic statistics are essential for effective policymaking, especially in countries where the informal economy plays a significant role. In addition, macroeconomic statistics can greatly contribute to a comprehensive picture of the informal economy beyond describing informal production and its contribution to GDP. Thematic and extended accounts on the informal economy can also include disaggregated labour accounts and identify the informal economy as a source of household income in the earned income account. Finally, the paper aims to contribute to an increased understanding between labour statisticians and national accountants regarding the macroeconomic perspective on the informal economy by clarifying the terminology used in the SNA and the 21^st ICLS resolution.

The fourth paper of this section is “Measuring the Informal Sector through Mixed Surveys: Past Experiences and Challenges Ahead” by François Roubaud (IRD). Taking stock of nearly four decades of experiences accumulated around the world, this paper describes the Informal Sector Mixed (households-businesses) Surveys (ISMSs), specifically designed to measure the informal sector in its different dimensions (employment, production, and relations with the rest of the economy) in a reliable manner. After exposing the theoretical principles, the paper addresses the main challenges of implementation in the field, detailing the advantages and limitations of this approach. Moreover, the compatibility of the ISMSs with the recommendations of the 21^st ICLS Resolution, concerning statistics on the informal economy, is questioned. In particular, the introduction of the dependent contractor category in the ICSE-18 adds a further degree of complexity in identifying informal economic units in the filter survey (LFS). The paper also addresses a number of challenges that still arise with this type of surveys, both at the methodological and institutional level. The discussion is illustrated with a set of selected empirical results drawn from surveys conducted in various countries.

In “Beyond “informal by default”: the future of contributing family work”, Jessica Gardner (UNFPA). focuses her attention on the often-overlooked role of contributing family workers, especially women, in the global economy. Historically sidelined in discussions on decent work, their working conditions and opportunities for formal employment have been neglected. Recent policy changes and revised standards for measuring informality are helping to shift this narrative, with new recognition that contributing family workers can hold formal jobs. The ILO's initiative to integrate a gender lens into these standards highlights the need for better data collection on this group. Accurate measurement, particularly disaggregated by gender, is crucial for effective policy interventions that can address their unique challenges. While some progress has been made, particularly in extending social protection, significant gaps remain, especially in low-income countries where most contributing family workers are based. A collaborative effort is required to implement these standards effectively, improve data collection, and advocate for policies that recognise and protect contributing family workers, leading to a more inclusive labour market and better conditions for all workers.

The sixth paper of this section is “Engendering the measurement of informality – statistical standards and methods” by Kieran Walsh (ILO). The new statistical standards for the informal economy, introduced in October 2023 by the 21^st ICLS, focus on the production of gender-relevant data through the adoption of a comprehensive conceptual framework and indicator framework. The ILO, through a project launched in 2021, aimed to provide evidence to inform the development of the standards, ensuring that they addressed gender issues and that measurement guidelines for country implementation would be available once they were adopted. Pilot studies in Uganda and Peru tested these standards, combining qualitative and quantitative methods to inform updated guidance and measurement tools. The paper also highlights the evolution of labour statistics since 2013, showing how interconnected standards now provide a better platform for analysing gender differences in working conditions. The new suite of standards adopted since 2013 significantly improve analytical possibilities for labour statistics, and countries are encouraged to implement them in labour force surveys. The ILO will continue to develop standards on key emerging areas like digital platform work and the care economy, maintaining a focus on gender equity.

The seventh paper of this section is “Informal work in sub-Saharan Africa: main findings from an opinion survey” by Rudolf Traub-Merz and Manfred Öhm (Friedrich-Ebert-Stiftung). The Friedrich-Ebert-Stiftung (FES), in collaboration with the ILO and IDOS, conducted a research project titled “Informal Employment, Social Security, and Political Trust in Sub-Saharan Africa.” Representative opinion surveys were conducted between 2018 and 2022 in six countries (Benin, Kenya, Senegal, Zambia, Côte d’Ivoire, and Ethiopia), interviewing over 11,000 households and 64,000 individuals. The project aimed to provide new insights into the social and political aspects of informal employment in African countries, exploring issues such as access to social protection, political trust, and self-organisation among informal workers. Key findings indicate that informal workers are eager to join health protection schemes and are willing to pay taxes if fair public services are provided. Many are organised in mutual assistance groups, highlighting the potential for collective action. The study also sheds light on issues of income inequality and distributional justice within informal employment. The results provide important data for policymakers aiming to improve social protection arrangements for informal workers and address their vulnerability.

In “Landownership and Informality in Agriculture”, Gayatri Koolwal (WIEGO Statistics Programme and The World Bank) illustrates the requirement to capture additional information to contextualise informality for those working as agricultural producers. Using nationally representative multi-topic surveys, which follow international standards and best practices on collecting self-reported, individual-level data on employment and assets, this paper highlights substantial differences in the socioeconomic profiles of agricultural producers in low-income contexts, as well as areas for improving survey data collection going forward. The findings show that the conditions of agricultural producers indeed vary widely in terms of consumption and land ownership. Importantly, compared with other individual and household socioeconomic variables, individual land ownership shows a strong correlation with improved welfare status and income for agricultural producers across countries. The findings underscore the importance of collecting individual-disaggregated data, especially on land ownership, and expanding the reference periods for agricultural surveys to better understand welfare outcomes of agricultural producers and opportunities for improving evidence-driven policymaking.

The ninth paper of this section is “Using household survey and administrative data to measure informality in Spain” by Miguel Angel Garcia Martinez and Sara Carrascosa García (Instituto Nacional de Estadistica). Following the adoption of the 21^st ICLS resolution, which enhances the applicability of the concept of informality for developed countries, this article presents an approach to measuring informal employment in Spain that integrates labour force surveys and administrative records. In countries with robust administrative systems, this approach could offer an improved indirect measurement of informal employment, avoiding the complications of self-reporting on irregular activities. In particular, by comparing microdata from the Spanish Labour Force Survey (EPA) with Social Security affiliation records, the study estimates the informal employment rate and examines the characteristics of informal workers, enhancing the understanding of labour market dynamics in Spain.

The tenth paper of this section is “Inequalities in job and income loss in countries with high prevalence of informal employment in Sub-Saharan Africa during the COVID-19 crisis” by Ivette Contreras, Gbemisola Oseni, Amparo Palacios-Lopez, Janneke Pieters, and Michael Weber (all from The World Bank). The paper uses high-frequency phone survey data from Ethiopia, Malawi, Nigeria, and Uganda to analyse the impact of the COVID-19 pandemic on employment and income in highly informal economies. The study tracks changes in work and income for individuals employed before the pandemic, with a focus on gender, age, education, family composition, and rural-urban differences. The analysis covers both short-term impacts (up to July 2020) and longer-term effects (up to February/March 2021). Key findings show that, early in the pandemic, women, young workers, and urban residents were more likely to lose their jobs, while income losses were widespread, particularly for households reliant on non-farm enterprises (NFE). By early 2021, job loss disparities based on gender and location had diminished, and education emerged as the main predictor of joblessness, with less educated workers being most affected. NFE income remained the most vulnerable source, both in the short and longer term. The study highlights the importance of targeting support toward less educated workers and formalising small informal businesses to improve resilience during crises. It also demonstrates the value of high-frequency phone surveys in tracking labour market changes in low-income countries.

The last paper of this section is “Key Indicators of Informality Based on Individuals and their Households (KIIbIH) database: Methodology and sources” by Thomas Manfredi and Alexandre Kolev (both from OECD). This paper describes the compilation of the OECD Key Indicators of Informality based on Individuals and their Household (KIIbIH) database, a new dataset that builds upon household surveys to provide comparable indicators and harmonised data on the socio-economic characteristics of informal workers in 50 countries across various regions. Unlike other data sources that capture greatest detail at the individual level, the KIIbIH database uses household surveys to capture socio-demographic and economic details with a particular focus on household level information. This household perspective is critical for understanding how the vulnerabilities of informal workers affect entire households and for designing policies that extend social protection measures to these workers. The KIIbIH dataset enables policymakers to explore key questions related to poverty, child benefits, social pensions, and the potential for covering informal workers through their household connections. It also offers insights into the contributory capacity of informal workers and the role of labour law enforcement in formalising employment. This comprehensive approach is essential for developing effective social protection strategies that address the needs of informal economy workers and their families.

2.2. The 2024 IAOS prize for young statisticians

The second section of the Journal publishes the winning papers of the Young Statistician Prize (YSP) of the International Association for Official Statistics (IAOS) for the year 2024. The YSP has been running since 2011, attracting submissions from across the world of statisticians who are less than 35 years old as of February of that year. With this prize, the IAOS seeks to actively encourage young statisticians to become members of the Association, promoting their involvement in the implementation of its activities. Today's young statisticians are tomorrow's leaders, and they inspire us, “older” statisticians, to think about the current and new frontiers in official statistics, promoting dynamic and innovative professional cooperation. In this section of the journal, the prize-winning manuscripts of the 2024 IAOS Young Statisticians Prize are celebrated by our colleague Gary Dunnet, who is the coordinator of this competition and has drafted this section of the editorial.

The Prize, along with the possibility to present the paper at an ISI/IIAOS conference, cash, and other associated opportunities, are very important not only for the prize winners but also for all participants. The judging of the prize is undertaken by a panel of eminent statisticians, and the SJIAOS articles are peer-reviewed, and the journal itself is well regarded and well-read across the Official Statistics community—all of this is good for one's resume or career progression opportunities. In addition, many National Statistical Offices of the submitted papers support young statisticians entering the Prize as a recognition of the remarkable methodological and analytical work performed by young statisticians in their organization. Even if you enter and are unsuccessful, you often reap some of the benefits highlighted above.

This year, 23 manuscripts from 21 countries were submitted, which is a signal of a healthy competition. The subject matter and statistical content of the submissions were generally of high quality; therefore, all authors should be proud of their work, whether they won or not. However, as they say, “there can only be one winner”, and this year the winning papers were the following:

The 1^st place 2024 YSP winning paper is “From COACH to COACH+: Automating Output Checking with Human-in-the-Loop” by Manel Sloken, Jel Vankan, and Peter-Paul de Wolf (Statistics Netherlands). The authors present a method (COACH + (COmputer-Assisted Output CHecking with Human-in-the-loop)) that integrates human expertise with machine learning algorithms to semi-automate output checking. The paper shows the promise of machine learning algorithms while underscoring the importance of collaborative efforts between human checkers and machine learning algorithms in ensuring the accuracy and reliability of output decisions.

The 2^nd place winning paper is “Including Non-Binary Gender in the Calibration Strategy for the Canadian Long-Form Sample Survey Weights”, by Alexander Imbrogno (Statistics Canada). The author proposes an alternative calibration strategy to incorporate small populations into the ‘standard’ calibration process while mitigating methodological concerns. The application of the proposed strategy to the non-binary gender diverse population is demonstrated; however, the solution can be extended to incorporate multiple small populations simultaneously while being adaptable to the calibration systems of other NSOs.

The 3^rd place winning paper is “RUMS – how to compare structures of enterprise groups?” by Adrian Urban and Simon Rommelspacher (Federal Statistical Office of Germany). The authors present a methodology (RUMS – Rommelspacher-Urban Metric for Similarity of enterprise groups) and its extension (RUMSA – Rommelspacher Urban Metric for Similarity of All enterprise groups) so that complex enterprise groups in a business register can be compared within and across countries. Not only does the paper provide a mechanism for comparability, but it potentially improves the quality of the business register(s).

Lastly, a special commendation was awarded to “E-Commerce Price Index Prediction with Time Series Mining and Automated Machine Learning” by Carmelita G Esclanda-Lo, Chelsea Anne Ong, and Gabriel Masangkay (Bangko Sentral ng Pilipinas, Philippines). The authors utilise advancements in Machine Learning and the availability of alternative datasets to delve into novel methodologies to ascertain a complementary index capable of aiding statistical agencies in analysing and forecasting the CPI.

All readers are encouraged to not only peruse the papers but also urge any young statisticians you know to consider entering the 2025 edition of the YSP competition; full details can be found at: https://iaos-isi.org/ysp.

2.3. Innovative statistical methods

This section of the Journal comprises five papers that show the richness and variety of the methodological research conducted in statistical and academic institutions. The focus of the papers ranges from testing survival models for analysing infant and child mortality, to introducing a dynamic microsimulation model for official population projections; from analysing the profile of immigrant groups using a symbolic data analysis approach, to using tourism satellite accounts to measure the direct and indirect evolution of tourism employment, to applying interregional input-output tables as an effective analytical tool to understand the regional interconnectivity of the food and beverage industry. These diverse papers offer valuable insights that can significantly contribute to the field of official statistics.

The first paper of this section is “Suitable Survival Models for Analysing Infant and Child Mortality Data” by Kumur John Haganawiga, Surya Kant Pal (both from Sharda University, India), and Anu Sirohi (Amity University, India). This study applies survival analysis to assess infant and child mortality using data from the 2018 Nigerian Demographic and Health Survey (NDHS). It identifies violations of the proportional hazards assumption in the Cox model, prompting the need for alternative approaches. Regularisation techniques like Lasso, Ridge, and Elastic Net are employed to refine model accuracy, with Lasso improving interpretability by removing less significant covariates. For parametric survival models, the Lognormal model is most effective for analysing infant mortality, while the Weibull model performs best for child mortality, as indicated by better statistical tests (AIC, BIC, and log-likelihood). These findings underscore the importance of selecting appropriate models for accurate mortality analysis. While the study's methodological insights are broadly applicable, the specific results are closely tied to Nigeria's socioeconomic and cultural context. Therefore, similar analyses should be conducted using country-specific data to ensure the models are well-suited to local conditions.

The second paper of this section is “STATSIM: Statistics Austria's dynamic microsimulation model for official population projections” by Pauline Pohl, Philip Slepecki (Statistics Austria), and Martin Spielauer (WIFO, Austria). In this paper, a dynamic microsimulation model developed by Statistics Austria to enhance population projections (STATSIM) is introduced. While the traditional cohort-component method is widely used for its simplicity and minimal data requirements, it struggles to capture complex demographic processes and provide detailed individual-level outcomes. With STATSIM, the authors first replicate the results of the cohort-component projections and then extend them with a new international migration module, which accounts for the length of stay and country of birth. This new model provides more realistic and consistent projections of emigration patterns compared to traditional methods. The gradual transition to a dynamic microsimulation model to improve population projections enables Statistics Austria to incorporate additional demographic and socio-economic variables over time. Future extensions will further enhance projections by considering heterogeneity in fertility, mortality, and employment status, providing more detailed insights into Austria's population dynamics.

The third paper of this section is “Immigrant Groups in Luxembourg's Labour Market - A Symbolic Data Analysis Approach” by Catarina Campos Silva, Paula Brito, and Pedro Campos (all from FEP, University of Porto). This study explores labour market profiles of different immigrant groups in Luxembourg from 2014 to 2022 using Labour Force Survey (LFS) data, Symbolic Data Analysis (SDA), and the Monitoring the Evolution of Clusters (MEC) framework. Immigrant groups were classified based on birthplace and length of residence, aggregated into symbolic objects described by key variables such as education and employment status. The results revealed that immigrants from the European Union and neighbouring countries share similar characteristics, while Portuguese immigrants have different profiles. Luxembourg nationals were found to be in between these groups. Notably, the study highlighted challenges in profiling immigrants from non-EU countries and emphasised the importance of urbanisation as a differentiating factor. This approach demonstrates the potential for replicating the analysis in other countries with high immigration rates, enabling cross-country comparisons of labour market trends. Moreover, combining SDA with the MEC framework is a novel contribution to official statistics, offering a dynamic view of immigrant profiles over time and informing more flexible immigration and labour market policies.

In “Tourism and Employment: New Tourism Satellite Accounts Results for Greece”, Stavros Hatzimarinakis (University of Patras, Greece) and Peter Hackl (Vienna University of Economics and Business) present a detailed analysis of tourism employment in Greece, focusing on both employment in tourism industries and tourism employment directly related to tourism demand. Between 2011 and 2019, the tourism industry saw an annual employment growth of 9.1%, while tourism employment grew by 11.6% annually. In 2019, approximately 810,000 people were employed in the tourism industry, with 427,000 of them directly attributable to tourism. Notably, accommodation and food services made up 76% of tourism employment. The Covid-19 pandemic in 2020 had a significant negative impact, with tourism industry employment dropping by 16.4% and tourism employment by 31.7% due to travel restrictions. Using the Tourism Satellite Accounts framework, the study provides a comprehensive picture of the sector's employment trends, offering valuable insights for policymakers and industry stakeholders. Despite Covid's impact, the steady pre-pandemic growth suggests that tourism will continue to be a key driver of labour market trends in Greece in the future.

The last paper of this section is “Optimising the Utilisation of an Interregional Input-Output Table in Measuring the Distribution of Value-Added Exports between Regions” by Siskarossa Ika Oktora (Politeknik Statistika STIS, Indonesia), Roni Anom Satrio, and Nora Muhtasib (Statistics Indonesia). This study explores the regional value chain of Indonesia's food and beverage industry using the 2016 Interregional Input-Output (IRIO) Table as an effective analytical tool to understand regional interconnectivity. The analysis focuses on backward and forward linkages to trace the origin and destination of value-added across Indonesia's regions. Provinces with high foreign value-added exports also show large domestic value-added, highlighting the industry's critical role in value creation at the regional level. The findings reveal that Java Island is the hub for both backward and forward regional interconnectivity, with Jawa Timur and Sulawesi Selatan identified as central provinces for the food and beverage industry. While backward linkages are prevalent and driven by the food, beverage, and agricultural sectors, forward linkages are led primarily by the food and beverage industry itself. This regional analysis demonstrates the industry's key role in driving economic growth in both Western and Eastern Indonesia.