BACK TO SCHEDULE REGULAR

Session 27

Statistics Under Development

4 June 2026
16:30 – 18:00
ŠIBENIK III

Presentation title
Filling Data Gaps in Official Job Vacancy Statistics
As labour shortages are said to be among the main challenges faced by the EU industry in the future, affecting both business activities and growth potential, it is essential to provide policy makers and social partners with adequate data to assess labour demand over time.

Read more Read less

Currently, this data need is only partially met by Eurostat’s official quarterly job vacancy statistics (JVS), collected based on Regulation (EC) No 453/2008. While JVS provides data by country and economic activity, it lacks the necessary detail at the occupational and regional levels. Expanding the scope of JVS is not anticipated, as it would incur significant costs and impose an undue burden on respondents.

In this paper, we demonstrate how Eurostat is addressing this data gap by exploring an alternative data source, namely Online Job Advertisements (OJA) data, collected through Eurostat’s Web Intelligence Hub. By combining JVS data with OJAs and EU-LFS data on the number of employees, we show how the total number of job vacancies and occupied posts, respectively, can be broken down by occupation and region.

Specifically, we explain how Eurostat (1) developed a methodology to bridge data gaps in official statistics, (2) assessed the quality of the novel data source on OJAs, and (3) uses OJAs and EU-LFS data on the number of employees to compile experimental statistics on labour demand by ISCO 3-digit occupation and NUTS 1 region.

By combining JVS data with this novel data source, we are able to offer detailed breakdowns that remain fully consistent with JVS totals. They are released as ‘statistics under development’, thereby filling the existing information gaps in official job vacancy statistics.

Main author / Presenter
Sofie Homa, Nevena Cholakova
Eurostat

Read more Read less

Sofie Homa holds a Master’s degree in Economics and works in Unit F.3 “Labour Market and Skills” at Eurostat. Sofie is responsible for the quarterly release of Job Vacancy Statistics (JVS) and leads the project on combining web data, specifically Online Job Advertisements (OJAs), with JVS totals. With the latter project, Eurostat aims to provide new insights on labour demand by occupation and region. Nevena Cholakova joined Eurostat in 2021, first working in the unit for Population and Demography. Since 2022, she has been a Statistical Officer in the unit dealing with Labour Market and Skills, where she leads the production and dissemination of the EU monthly unemployment rate and also contributes to quarterly ?U Labour Force Survey (EU LFS) products. In this context, in 2025 Nevena was responsible for carrying out the first quality monitoring exercise of the EU monthly unemployment rate.

CO-AUTHOR:

Presentation title
Integrating MNO data in the official tourism statistics from the demand side
Tourism is a constantly evolving phenomenon with a significant impact at local level. This poses new challenges in terms of measurement and requires very detailed geographical data.

Read more Read less

Traditional statistics (surveys at borders, in households or in tourist accommodation) have the usual limitations due to sample designs and budget constraints, which prevent them from providing very detailed information.

This is why it is necessary to seek new sources of information that improve granularity.

On the other hand, the widespread use of mobile phones and the traceability of their position on antennas suggests that the data stored by mobile phone operators has great potential for accurately and detailed measurement of tourist movements.

Since 2021, the INE has been publishing three experimental statistics using mobile network operator data (MNO data) and working closely with several companies to transform their positioning data into counts of tourist trips, overnight stays and excursions.

In 2026, an important step will be taken in measuring inbound tourism, as this rich information will be integrated into the statistical process, incorporating data from administrative records and a small-scale border survey to identify the variables that characterise travel and expenditure, which are essential and cannot be obtained by other means. The result of this procedure will be label as official statistic.

This paper will describe the collaborative work carried out with operators and the type of information received from them. It will also describe the administrative records considered and the characteristics of the survey conducted (sample sizes, collection method and questionnaire).

The integration of survey, MNO data and administrative data is carried out using a general linear state space model. Thanks to this model, all sources of information are combined to obtain more accurate data.

Specific treatments are also carried out to resolve specific issues such as:

- Lack of knowledge about visitors' use of their phones during their trip.

- The overestimation of foreign tourists in border municipalities.

-Transport drivers who should not be classified as visitors but are counted in mobile data.

Finally, the dissemination and visualisation of the results will be described.

An assessment will be made of the pros and cons of this project, as well as the knowledge acquired regarding access to private databases.

The project to use MNO data to calculate estimates of outbound and domestic tourism will also be presented, improving both the timeliness of the information available and, of course, its granularity.

Main author / Presenter
Marta Sixto
NSI Spain

Read more Read less

Marta Sixto has a degree in Mathematics and a master's degree in the same field. She has more than ten years of experience at NSI Spain, where she has been involved in the development of official statistics. Throughout her career, she has participated as a representative in international meetings and forums. For the past five years, she has been working in the area of tourism, where she compiles statistics on inbound tourism. She is also involved in two statistical innovation projects, focusing on the use of mobile phone data to measure tourism flows and the use of bank card transaction data to estimate tourism expenditure

CO-AUTHORS:

Presentation title
Exploring the use of bank card transaction data for early economic indicators
The demand for more timely, granular, and policy-relevant short-term statistics has intensified in recent years.

Read more Read less

This puts pressure on National Statistical Institutes (NSIs) to modernise production processes to increase timeliness, while reducing response burden on businesses. This paper discusses ongoing work at the National Statistics Office (NSO) Malta that explores the potential use of bank card transaction data as an alternative and complementary source for monthly turnover statistics.

The NSO receives monthly bank card transaction micro-data. This data is available substantially earlier than the standard t+30 days release schedule for survey-based turnover statistics. This paper discusses the methodology implemented to produce transaction-based measures, and their comparison to those produced using official survey data. The analysis focuses primarily on retail trade, with planned extensions to accommodation services and food and beverage service activities. Key methodological challenges related to population definition, comparability, and data integration will be presented. Comparisons are carried out at both micro and aggregate levels to assess coherence. Benchmarking techniques are applied to evaluate alignment in trends and seasonal patterns, while sensitivity analyses are used to assess the robustness of results to alternative methodological assumptions. The feasibility of producing more detailed monthly indicators, such as turnover indices for specific retail sub-sectors including supermarkets, is also investigated. The work is ongoing; however, initial analyses indicate that bank card transaction data have the potential to provide timely and informative signals of economic activity in retail trade.

This analysis contributes to the growing body of work on the use of alternative and innovative data sources in official statistics. The study addresses key strategic priorities for NSIs, including improving timeliness, reducing response burden, and enhancing the analytical value of short-term statistics.

Main author / Presenter
Sam Sacco
National Statistics Office

Read more Read less

Sam Sacco is Head of Unit for Short-term Business Statistics (STS) at the National Statistics Office (NSO) of Malta, with 15 years of experience in official statistics. He holds a bachelor’s degree in economics from the University of Malta and a master’s degree in Economic Policy from the University of London. He has represented the NSO in Eurostat’s STS Working Groups and Task Forces. His work includes overseeing the production of monthly and quarterly statistical outputs covering early indicators such as turnover, production, producer prices, and building permits. His areas of interest include imputations, index calculation, and seasonal adjustment.

CO-AUTHOR:

Presentation title
Production and validation of experimental indicators based on Italian OJAs
Online job advertisements (OJAs) are emerging as a new data source for monitoring labour market dynamics and emerging occupational and skill needs.

Read more Read less

Recent work by Eurostat on producing experimental statistics based on OJA data has demonstrated this data source's relevance, particularly for producing labour shortage indicators. However, when using OJA data, it is important to recognise its limitations in terms of quality and potential biases. A key issue is vacancy coverage, as a significant proportion of vacancies are not advertised online. There is also a biased representation of the labour market, with certain types of jobs being under- or over-represented.

This work aims to assess the feasibility of producing national experimental indicators based on OJAs data, that go beyond the indicators produced by Eurostat, using the microdata and services of the Web Intelligence Hub (WIH) infrastructure. This work is being carried out within the mono-beneficiary project financed by Eurostat for Italy and other single European countries. Producing new experimental statistics is essential to supplement traditional labour demand statistics, as achieving a similar level of detail in terms of occupation, skill and territorial level would otherwise be very costly and involve a considerable statistical burden. The work also analyses persistent quality issues in OJA data and suggests possible solutions. This helps to ensure that the use of OJAs in statistical production meets the required quality standards, albeit on an experimental basis.

In order to assess the accuracy and robustness of experimental indicators, this work adopts a methodological approach articulated on several levels of analysis. These include: the landscaping and relevance of web sources from which OJA data are extracted; the stability of sources over time; benchmarking analysis; representativeness analysis of OJA data by occupation and skill, comparison of the distribution of OJA data with that of other official sources (e.g. Labour Force Survey and the Italian Excelsior information system); longitudinal analysis of produced indicators; time series comparison of produced indicators with other general and sectoral macroeconomic indicators interrelated with labour market dynamics (e.g. monthly employment rate, GDP trends, industrial production index, construction production index and services turnover index).

The quality of the experimental statistics is fundamental to the effective and credible use of OJAs within the statistical system. This requires continuous updating, monitoring and critical reflection on the OJA data used as input, the methods employed and the accuracy and consistency of the resulting output.

Main author / Presenter
Annalisa Lucarelli
Istat

Read more Read less

Annalisa Lucarelli is senior researcher and responsible for the production of quarterly indicators on job vacancies and hours worked at the Italian National Institute of Statistics (ISTAT). Building on the ESSnet projects on Online Job Advertisements (OJAs) launched in 2018, she currently plays a key role in the Italian Eurostat-funded project aimed at developing experimental indicators based on OJA data.

CO-AUTHORS:

Presentation title
Developing fit-for-purpose quality targets for Statistics under Development
The amended Regulation (EC) 223/2009 on European Statistics, which entered into force on 26 December 2024, introduces the concept of ‘Statistics under development’ (SuD).

Read more Read less

Statistics under Development can be defined as newly created or significantly revised statistical outputs and insights produced by Eurostat and the NSIs that are in the phase of development, testing, validation, and improvement with the aim of integrating them in the regular production of European Statistics. While the new legal provisions regarding SuD explicitly state that they do not need to fulfil all the quality criteria expected of European statistics, they are eventually expected to satisfy them. This raises the question of how to best assess the maturity of a SuD statistical output from a quality perspective.

The process framework for SuD recently approved by the ESSC proposes a way forward in this regard. It foresees that, for each SuD statistical output, a target quality profile should be defined. This target profile should set explicit targets for each quality dimension and ensure that the weighting of each quality dimension is aligned with the expectations and needs of the prospective users of the specific output. The target quality profile, once established, represents the reference against which the maturity of each SuD will be benchmarked. In this contribution, the authors will discuss options for establishing a target quality profile and adapting it according to the nature of statistical outputs, data sources and methods involved

Main author / Presenter
Jean-Marc Museux
Eurostat

Read more Read less

Jean-Marc Museux is a Senior Expert and Enterprise Architect at Eurostat, the statistical office of the European Union. He is actively involved in innovation and capacity building across the European Statistical System, with a particular focus on the reuse of non-conventional data sources and the integration of emerging technologies such as artificial intelligence in official statistics. With extensive experience in international cooperation and statistical modernization, he contributes to shaping innovation initiatives that enhance the quality and relevance of official data in an evolving data ecosystem. A statistical methodologist since 1997, Jean-Marc began his career at Statistics Belgium and has been with Eurostat since 2001. He holds a ph.D in Physics from the Free University of Brussels.

CO-AUTHOR: