Abstract

Data has the potential to impact millions of lives, as it has become critical to government decision making. Just as data gathered by a doctor can help improve a patient’s diagnosis and ultimate well-being, data gathered by government organisations, international organizations, research institutions, and civil society can improve social well-being by enhancing service delivery, prioritizing scarce resources, holding governments accountable, and empowering individuals [1].
The main objective of all national statistical institutes is to produce official statistics with the highest possible quality. We must at all times strike a balance between the quality requested and the practical and economical realities [2]. The response rates in surveys are decreasing and at the same time more granular data are required. Therefore, statistical institutes must look for new sources of data - both by using already known administrative data (the existence, completeness, availability of which varies in the countries) and by looking for new, privately held data.
Latvia has many high-quality, regularly updated registers and databases with a good coverage, such as the Office of Citizenship and Migration Affairs, the State Revenue Service and other state information systems, as well as other registers and databases where information on both individuals and dwellings is available. At the same time there is a lot of privately held data that can provide necessary information for statistics – for example, personal purchases in stores.
One major factor that facilitates the statistical reuse of administrative data records is the use of unified identification systems across different sources [3]. In Latvia, single personal identifier (personal identification number) is used in all state registers and databases. It allows data linkage to provide better data coverage, develop methods that are based on data from several sources, to produce new variables. In contrary, privately held data lack identification numbers and national statistical institutes are challenged to look for possibilities to link privately held data with other information without ID codes (for example, link with demographic or socio economical information, with households).
Central Statistical Bureau of Latvia has actively pursued the possibilities for data linking. This endeavour aims to yield an innovative statistical product tailored to the specific requirements of decision-making processes or data collection process innovations. New variables (for example, on graduates, on students, incl. from third countries), more granular data (also allowing to track changes over time) provide additional value in decision making process. In addition, new data sources to supplement survey data, for example, information from retail chains, allow to improve quality of data. References 1 World Bank (2021) World Development Report 2021: Data for better lives. World Bank, 2021. Available at: https://www.worldbank.org/en/publication/wdr2021 2 Barca V., Hebbar M., Knox-Vydmanov C., Brzezinska I. (2023) We have the data, let’s use it better. Pushing the boundaries of social protection administrative data analysis and use. Deutsche Gesellschaft fūr Internationale Zusammenarbeit (GIZ) GmbH, 2023.
Available at: https://socialprotection.org/sites/default/files/publications_files/GIZ-%20Use%20Admin%20Data%20Social%20Protection.pdf 3 Tønder J.K. (2008) The Register-based Statistical System. Preconditions and Processes. International Association for Official Statistics Conference Shanghai October 14 – 18, 2008. Available at: https://www.fao.org/3/I9360EN/i9360en.pdf