BACK TO SCHEDULE SPEEDTALK

Speed talk session 8

From Metadata to Trust

4 June 2026
13:15 – 14:00
ŠIBENIK IV

Presentation title
Beyond the NSI: building sustainable Quality Reporting in Official Statistics
In its role as coordinator of the Italian national statistical system (Sistan), Istat has progressively strengthened the national quality framework in close alignment with the measures and tools developed within the European Statistical System (ESS).

Read more Read less

Following the release of the national version of the European Statistics Code of Practice and the adoption of a national Quality Assurance Framework, Istat has completed the final step in this process by establishing a structured and operational approach to quality reporting. This initiative aims to reinforce transparency and trust in official statistics, while ensuring feasibility, proportionality and long-term sustainability for statistical producers operating within a highly heterogeneous institutional system. The national quality reporting framework is grounded in an extensive analytical effort conducted within Istat, based on a systematic review of metadata disseminated by Sistan entities for nearly 400 statistical outputs across a wide range of domains. This large-scale assessment required substantial methodological work, strong interdepartmental coordination and a detailed examination of existing dissemination practices. It provided a comprehensive and evidence-based overview of how metadata are currently documented. Drawing on the results of this empirical analysis, Istat identified a nationally relevant subset of the SIMS, introducing only limited and targeted adjustments. This approach ensured consistency with the ESS conceptual framework, while reflecting the concrete production conditions, capacities and constraints of the Italian statistical system. The outcome of this process is a simplified national template for quality reporting, supported by detailed operational guidelines. The guidelines, currently available in Italian only, mirror the structure, terminology and conceptual logic of the ESS Handbook for Quality and Metadata Reports, while being calibrated to the national context. Together, the template and the guidelines promote harmonised documentation of statistical processes and outputs and support a shared understanding of quality concepts. To facilitate practical implementation, the guidelines include examples drawn from real statistical outputs for which Sistan entities act as data producers. These cases illustrate how quality reports can be populated in concrete operational settings, supporting understanding, consistency and uptake across different types of producers. A core design principle of the framework is the reduction of reporting burden. The template is designed to reuse metadata already collected during the preparation of the National Statistical Programme, enabling alignment and consistency checks between planning and dissemination phases. This integration improves metadata coherence, strengthens quality control mechanisms and contributes to the long-term sustainability of the initiative.

Main author / Presenter
Andrea Bruni
Istat

Read more Read less

Andrea Bruni has been working at Istat since 2001, actively participating in national and European working groups. He has extensive experience as an expert and team leader in consultancy and international cooperation projects, focusing on data and metadata exchange, data quality, and information systems. Throughout his career, he has contributed to the development and implementation of quality assurance frameworks in statistical processes. In addition to his project work, he has served as a tutor for foreign delegations and has delivered training courses at various levels. For many years, he has been a lecturer for the Advanced Quality Reporting course within the European Statistical Training Program (ESTP), where he shares his knowledge and expertise on quality reporting practices, helping to shape the next generation of professionals in the field.

Presentation title
Who Are You, According to the Register? Tracing Nationality Errors in Administrative Data
Administrative data are increasingly central to the production of official labour market and migration statistics and are often treated as a benchmark for data quality.

Read more Read less

This paper examines the quality of nationality information in German administrative labour market data by exploiting a rare linkage between survey and administrative sources. We use data from a the large-scale online migration survey “International Mobility Panel of Migrants in Germany” (IMPa), linked at the individual level to administrative labour market records from the “Integrated Employment Biographies” (IEB) that merges various administrative data sources to create detailed, day-by-day records of individuals' labor market histories in Germany. Assuming that survey-reported nationality is correct, we assess the extent, persistence, and determinants of discrepancies between nationality information recorded in the survey and in administrative sources.

We distinguish four types of classification outcomes: correctly classified individuals, Germans misclassified as foreigners, foreigners misclassified as Germans, and foreigners with an incorrect nationality recorded. These error types are analysed overall and separately by administrative source, distinguishing employer reports from records generated by job centres and employment agencies. In addition, we examine the contexts in which nationality errors are most likely to occur and how long they persist over time.

In a second step, we assess the quality of administrative metadata by analysing whether the timing of first occurrences in administrative records can be used as proxies for key migration-related events reported in the survey. Specifically, we study the time lag between survey-reported entry into Germany and the first administrative notification, as well as between the reported year of acquisition of German citizenship and the first occurrence of German nationality in administrative data. We document substantial heterogeneity across countries of origin and socio-demographic groups, highlighting conditions under which such metadata-based approximations are more or less reliable.

Finally, we propose a practically implementable imputation strategy that exploits differences in reporting quality across administrative sources. By prioritising higher-quality sources and correcting implausible isolated changes in nationality, the approach substantially reduces misclassification rates. Our findings demonstrate that administrative data quality varies systematically by source and institutional context and that targeted quality management strategies can significantly improve the reliability of key variables. The results have direct implications for the production, interpretation, and quality assurance of migration-related indicators based on administrative data in official statistics.

Main author / Presenter
Simon Wagner
Institute for Employment Research (IAB) of the German Federal Employment Agency (BA)

Read more Read less

Simon Wagner is a PhD student in economics in the joint doctoral programme in labour market research of the Institute for Employment Research (IAB) and the School of Business, Economics and Society of the University of Erlangen-Nuremberg (FAU), and is affiliated with the doctoral programme “Quantitative Economics” at Kiel University. He works as a research associate at the IAB of the German Federal Employment Agency (BA), Department of Migration and International Labour Studies (INTER). Simon holds a Bachelor’s degree in economics from the University of Mannheim and a Master’s degree in economics from the University of Göttingen. His research interests focus on the economics of migration and integration, survey methodology, and administrative-data-related research on data quality and survey–administrative data integration.

CO-AUTHOR:

Presentation title
An Integrated Collaborative Platform for Industrialized Statistical Production via GSBPM-Driven Workflows
The modernization of National Statistical Offices (NSOs) necessitates a transition from fragmented, siloed methodologies toward standardized, industrialized production chains.

Read more Read less

This paper proposes a collaborative platform designed to operationalize the Generic Statistical Business Process Model (GSBPM) as a functional workflow management engine. The platform structures statistical production by treating each GSBPM sub-process as a discrete functional unit defined by specific inputs,tasks, and outputs.

The system architecture implements a granular role-based access control model involving managers, validators, and collaborators. While managers oversee the global progress of multiple workflows, the production level is governed by a rigorous validation cycle: collaborators execute tasks and request validation, while validators maintain the exclusive authority to approve outputs or finalize deliverables. To enhance efficiency, the platform supports semi-automated sub-processes through a remote Python execution environment. This feature allows code to be executed directly on input datasets, with resulting outputs stored as deliverables; however, the workflow transition remains gated until a human validator approves the automated results.

The primary contribution of this tool is the shift from retrospective evaluation to real-time monitoring. By embedding data collection for Quality Indicators (QIs) directly within the GSBPM sub-processes,the platform enables NSOs to capture quality metadata during the production phase. This ensures a transparent, auditable, and industrialized production chain that aligns with international standards for official statistics.

Main author / Presenter
Abderrahmane Chahbi
High Commission for Planning (Morocco's NSO)

Read more Read less

Head of Infrastructure and Statistical Platforms Operations at the High Commission for Planning, with 13 years of experience spanning infrastructure management, system architecture, and the development of platforms across the statistical data lifecycle. Member of the HCP Strategic Committee for Digitalization, the National Committee on Open Data, and other national and international coordination bodies.

Presentation title
Publication thresholds and data quality: lessons from Estonian Labour Force Survey
Publication thresholds are essential for ensuring the reliability of sample survey estimates and guiding decisions on data dissemination.

Read more Read less

They indicate whether an estimate can be published or should be flagged for caution. Eurostat applies two reliability flags:

• Limit A – Data should not be published.

• Limit B – Data may be published with a warning about limited reliability.

Across EU countries, publication thresholds are most commonly based on the coefficient of variation (CV), the number of observations (NOBS), or a combination of these measures. Each country determines its own method to calculate publication thresholds.

In 2023, Statistics Estonia revised the publication thresholds for the Estonian Labour Force Survey (ELFS) to improve consistency and reliability. The revision involved analyzing practices in other EU countries and testing three approaches for quarterly estimates, all producing similar results.

Previously, ELFS applied CV limits of 30% for suppression and 20% for publication with warning. Based on our analysis and wanting to keep consistency between Eurostat thresholds and our national publication we conclude that CV 25% would be more suitable for limit A as it applies better to our national rule that estimates based on fewer than 20 responses are not published.

The paper provides an overview of the tested approaches, their results, and the rationale behind the chosen threshold. It also highlights ongoing efforts at the European level: Eurostat has established a Task Force on Publication Thresholds with the objective of drafting non-binding guidelines to harmonize practices across member states.

Main author / Presenter
Kristi Lehto
Statistics Estonia

Read more Read less

I am a leading methodologist in Statistics Estonia.

CO-AUTHOR: