Day 3 (Room C, July 3) - The 5th Congress of Polish Statistics

Objective

The paper aims to develop and evaluate, using Polish data, a simple spatiotemporal method for disaggregating annual regional GDP series to quarterly frequency using a smoothing algorithm, and to compare its results with a multivariate regression-based approach that uses auxiliary variables.

Methods

The method assumes that the disaggregated series should exhibit minimal fluctuations while satisfying balancing constraints: regional quarterly sums must match the annual regional data, and the sum of regional quarterly values must equal to the national quarterly figure. The resulting optimization problem is solved via an interior-point algorithm. Its sequential variant requires revising only the most recent disaggregated series when data for a new year become available. A regression model with four benchmarks is used for comparison.

Results

The sequential smoothing method produced quarterly regional GDP growth rates with a level of smoothness comparable to national data while still capturing local variations (e.g. the COVID-19 downturn). A comparison with the one-step version confirmed almost identical results. Against the regression-based approach, average differences in annual growth rates reached up to 0.8 percentage points, with correlation coefficients exceeding 0.87. Forecasting performance analysis indicated that the smoothing method is competitive with regression when series are short or horizons are brief.

Conclusions

The proposed procedure is computationally simple, requires no auxiliary indicators, and can be implemented by statistical offices lacking long, high-quality regional data series. Its sequential variant minimizes historical revisions while maintaining close agreement with regression-based methods. Combining smoothing with a regression-based approach could be considered for further improvement.

Keywords

regional GDP, temporal disaggregation, nowcasting, smoothing algorithm, interior point optimization

Objective

For many years, the public debate in Poland has highlighted the issues of urban sprawl and spatial chaos. While various monitoring datasets exist, there is a lack of nationwide, high-resolution spatial statistics. Available land use data often fail to capture the functional aspects of urban areas. The aim of this study is to identify and analyze the functional land use structure of Polish cities using a consistent methodology based on official spatial data, as well as to examine changes between 2017 and 2024.

Methods

The research method is based on the concept of the urban transect. Functional land use analysis was conducted using data from the Land and Building Register (EGiB), with 500 m2 hexagons as the basic unit of analysis. Based on land use structure, the hexagons were classified according to a defined functional typology. To reflect the specific characteristics of Polish cities, two additional categories were introduced: residential development on agricultural land and high-density multifamily housing areas.

Results

The conducted analyses allowed for the identification of the functional and spatial structure of cities, enabling an objective characterization of urban land use and an assessment of its temporal changes. Based on the results, it is possible to broadly identify spatial reserves within cities for potential future development and to indicate the likely directions of urban expansion. The findings also revealed the intensity of uncontrolled and chaotic suburbanization processes.

Conclusions

Due to its high level of automation, ongoing data updates, and relatively easy access, the proposed research method offers a viable alternative to traditional studies of the functional and spatial structure of cities. The resulting data – accurate yet standardized and generalized – effectively reflect changes occurring in urban space, making them a valuable source for analyzing the evolution of spatial structure over any selected time period.

Keywords

urban space, LULC, EGiB, GIS

Objective

This study proposes a new density-based metric for measuring spatial competition among urban retailers. It integrates population distribution and firm locations using Voronoi tessellation to define zones of influence. Inspired by ecological competition models and spatial econometrics, the method addresses limitations of traditional approaches and supports practical applications in urban planning, retail strategy, and antitrust analysis.

Methods

Retail locations from OpenStreetMap are cleaned using spatial clustering and medoid selection. Voronoi polygons define each facility`s influence zone within Warsaw. Population data from the Polish Census is proportionally assigned to each zone. Population density serves as a spatial weight to compute standardized market share indices and a spatially weighted Herfindahl-Hirschman Index (HHI).

Results

Applied to Biedronka and Lidl supermarkets in Warsaw, the method reveals that densely populated areas yield higher market influence per store. Spatially weighted HHI values differ notably from traditional metrics, exposing deeper patterns of market dominance. Results show the model’s ability to correct for spatial distortions in raw data and better reflect real competitive dynamics.

Conclusions

The proposed metric offers a replicable, data-driven tool for evaluating competition in urban environments. It improves the understanding of firm influence, supports equitable access assessments, and enhances decision-making for retail and urban policy. The method is adaptable to other sectors and cities using open data, and bridges ecological theory with spatial economic analysis.

Keywords

spatial competition, Voronoi tessellation, urban retail, market concentration, population-weighted index

Objective

The aim of the paper is to present the assumptions of the Integrated Analytical Platform - a planned platform to support the initiation and implementation of research using data from public records.

Methods

The paper presents the results of the 'Integrated Analytical Platform' project, implemented in partnership between public institutions (Minister of Digitalisation, Minister of National Education, Minister of Family, Labour and Social Policy, Minister of Health) and academic institutions (University of Warsaw, SGH Warsaw School of Economics).

Results

The result of the project is a prototype of an analytical solution supporting conducting analyses on the basis of combined data from different public registers: the main assumptions of the methodological approach to the use of ZPA as a tool for cooperation between public administration and research centres are presented.

Conclusions

Conducting analyses based on data from public registers is key to building evidence-based knowledge. Pilot research within the Integrated Analytical Program project demonstrates the potential of using administrative data to conduct analyses of public policy instruments.a

Keywords

administrative data, evidence-based policy

Objective

The aim of this study is to present the role of reintegration units in preventing social exclusion in Poland between 2015 and 2023. These units implement social and professional reintegration services targeted at long-term unemployed individuals, persons with disabilities, people leaving penitentiary institutions, and the homeless. Their operation was strengthened by the Act on social economy of 2022, which defined their status within the social economy sector and assigned them a key role in implementing the objectives of the National Programme for the Development of Social Economy.

Methods

W analizie wykorzystano dane pochodzące wyłącznie ze źródeł administracyjnych: systemów informacyjnych urzędów wojewódzkich, Ministerstwa Rodziny, Pracy i Polityki Społecznej oraz Państwowego Funduszu Rehabilitacji Osób Niepełnosprawnych. Wyniki W 2023 r. działało 1246 jednostek reintegracji społeczno-zawodowej – o 17 mniej niż rok wcześniej, ale o 57 więcej niż w 2015 r. W ciągu 2023 r. z usług reintegracji społeczno-zawodowej skorzystało blisko 49,0 tys. osób zagrożonych wykluczeniem społecznym, tj. o 2,1% więcej niż w 2022 r. W latach 2015-2023 ich liczba wzrosła o 21,6%. Działalność prowa

Results

In 2023, 1,246 units providing social and professional reintegration services were active—17 fewer than in 2022, but 57 more than in 2015. Nearly 49,000 individuals at risk of social exclusion benefited from reintegration services in 2023, representing a 2.1% increase compared to 2022 and a 21.6% increase compared to 2015. Most of the entities focused on activating people with disabilities—733 occupational therapy workshops and 141 vocational activity establishments.

Conclusions

Reintegration units play an important role in preventing social exclusion by supporting individuals at risk of marginalisation in returning to the labour market and active social life. Ongoing monitoring of reintegration units is essential to assess the impact of their services on the economic independence of individuals at risk of social exclusion, which is crucial for effective social policy and sustainable social development.

Keywords

Reintegration units, social exclusion, social and professional reintegration services, social economy

Objective

The objective of this presentation is to present the findings of an experimental study focused on identifying the occupations held by individuals actively engaged in the national economy (excluding the unemployed).

Methods

The study utilized data drawn from administrative registers and statistical surveys conducted by official statistics. A key innovative element was the approach that considered all employment positions held by an individual, regardless of the type of contract. This enabled a more comprehensive capture of actual professional activity. The research focused on the occupation actually performed, rather than the one formally acquired through education or training. This required precise identification of the nature of work performed in a specific place and time.

Results

The resulting data open up new opportunities for labor market analysis by allowing for a detailed representation of employment structures by actual occupation, broken down by demographic, territorial, and sectoral dimensions.

Conclusions

This study holds considerable relevance for both socio-economic policy and vocational and educational planning, supporting evidence-based decision-making (data-driven policy). It opens new perspectives for monitoring structural changes in the labor market and for improving the alignment of the education system with the real needs of the economy.

Keywords

labour market, occupation held, administrative data

Objective

The presentation aims to show how modern tools of the official statistics system – based on administrative data – are revolutionising the way wages and salaries are analysed and enabling a more dynamic and detailed view of the labour market.

Methods

The Survey on the Distribution of Wages and Salaries in the National Economy is entirely based on administrative sources – mainly registers of the Social Insurance Institution (ZUS).

Results

The results of the survey provide a unique and regularly updated picture of wage differentiation in the national economy. The data are published at a monthly frequency, with an approximately five-month lag from the reference period, which ensures that the wage situation can even be monitored on an ongoing basis. The first data published in September 2024 concern January, February and March 2024. The results of the survey are published in the form of a news release and a set of tables. The data are presented with breakdowns both by characteristics of a person earning a wage or salary (sex, age,

Conclusions

The use of administrative data in statistical surveys is not only in line with global trends in modern statistics systems, but is becoming the foundation for a more responsive and accurate description of socio-economic phenomena. The range of published data and information is being expanded. Data on wages and salaries published every month allows the phenomenon to be analysed using the average wage / salary and the median wage / salary with unprecedented detail. These statistics are becoming a dynamic tool for monitoring changes and making decisions in near real time.

Keywords

wages and salaries, distribution of wages and salaries, median wage / salary, average wage / salary

Objective

The aim of the paper is to present the characteristics of relative indicators for monitoring the labour market entry of graduates used in the Polish ELA system, from the perspective of their application for comparing the entry of graduates into the labour market over time (individual cohorts) and in space (locally, but also internationally).

Methods

The analyses use data from the ELA system, based on a combination of information from two public registers: POL-on and ZUS (Social Insurance Institution), as well as data from graduate monitoring systems in selected countries (the Czech Republic, Slovakia, Hungary, Romania). Relative earnings ratios compiled from data from these systems are comparable.

Results

The obtained data confirm the good properties of relative employment rates for comparisons over time and space. Moreover, these indicators are internationally comparable, as confirmed by pilot analyses conducted using graduate tracking systems in 4 European countries.

Conclusions

The innovative relative indicators used for the first time to monitor the higher education graduates in Poland have characteristics that allow them to be used for international, local and also temporal comparisons.

Keywords

graduates tracking, monitoring employment, relative earnings

Objective

A comprehensive framework identifying and examining the multifaceted problems (technical, governance-related, legal, ethical, economic, operational, socio-cultural) impeding the successful development, deployment and sustained operation of public sector data spaces, and to understand their interdependencies and collective impact is the aim of the presentation.

Methods

The study is based on an extensive review and synthesis of the academic literature, policy documents, government reports and case studies of European public sector data space initiatives. It utilizes a qualitative approach, analyzing documented challenges and lessons learned to build a comprehensive taxonomy and analytical framework of problems.

Results

The key findings reveal a wide spectrum of interconnected problems in building public sector data spaces. These span technical, governance, economic and socio-cultural dimensions, often creating compounding negative impacts.

Conclusions

The research provides a comprehensive taxonomy of the challenges, informing policy and practice for more effective public sector data space implementation. It underscores the need for holistic strategies addressing technical, governance, economic and socio-cultural issues to realize public value, foster innovation and retain citizen trust. A future research agenda is proposed to tackle unresolved problems and guide sustainable development.

Keywords

data spaces, public sector, data governance, European data strategy, digital transformation, data sharing, legal frameworks

Objective

In the face of dynamic social, economic and technological changes, official statistics require not only tools to respond to the emerging information needs but, above all, the ability to anticipate those needs and turn them into new development opportunities. This necessitates the development of a culture of innovation. The aim of this presentation is to outline the ways in which the innovation culture is being fostered within official statistics, and to indicate directions for further action.

Methods

Using a systemic approach, we create internal conditions for testing new solutions, support teams experimenting with alternative data sources and novel analytical methods (including AI, big data and the integration of administrative data), and promote cross-sectoral cooperation – with the private sector, academia and public administration – as well as international collaboration. We understand innovation not only as the adoption of new technologies but, above all, as an attitude of openness to change, learning and continuous improvement.

Results

Statistics Poland's activities contribute to strengthening the capacity of official statistics to test new solutions, make better use of data and enhance collaboration with stakeholders. There is a noticeable increase in awareness and organizational readiness to implement change and openness to new approaches. It is essential that innovative thinking is embedded not only in analytical and methodological efforts but also in everyday interactions with data users.

Conclusions

Building a culture of innovation in statistics is a long-term process that requires a systemic approach, support for experimentation, and both internal and external collaboration. Statistics Poland's experience shows that innovation can be a lasting source of value in statistics – methodologically, organizationally, and socially.

Keywords

innovation, strategy, cooperation

Objective

The aim is to present the possibilities of calculating price indices and rents for commercial real estate (retail, office, warehouse) in Poland.

Methods

The methodology usually takes into account the various types of indices calculated, mainly hedonic: time dummy, rolling time dummy, repricing, average characteristics, imputation, stratification method.

Results

The choice of the method for estimating the index depends on the amount of statistical information available in the database. More extensive databases, which include information such as property characteristics, allow for the calculation of hedonic indices, for example, using the rolling time dummy method.

Conclusions

Improving the quality of rental and commercial property price indices requires obtaining additional sources of data on commercial properties (other than the Property Price Register).

Keywords

price indices, rent indices, commercial real estate, hedonic indices