Statistika: Statistics and Economy Journal - No. 1/2025

Statistika, 105(1): 5–17
https://doi.org/10.54694/stat.2024.42

Abstract
Research of controversial topics (drug consumption, corruption) requires reliable estimates of population means of sensitive variables (spending on drugs, illegal sources of income). To avoid non-response and fabricated responses surveys using randomized response techniques (RRT) for quantitative variables are conducted. The paper focuses on surveys conducted regularly in time to study evolution of population mean of a sensitive variable. This topic has not been explored for RRT yet. In applications of RRT is critical a choice of its parameters. The goal is to find rules of thumb if mean of a sensitive variable change in time. We focus only on methods using dichotomous variable (Antoch et al., 2022), because they were designed for variables with many values (Vozar and Marek, 2023). The different scenarios are applied on the Czech and Slovak wage data from Average Earnings Information System in years 2017–2019 using prior information. The scenarios evaluated in extensive simulation study focusing both on mean wage and year-on-year growth.

Keywords
Randomized response techniques, dichotomous response, wage distribution, survey sampling, comparability over time, population mean

Statistika, 105(1): 18–32
https://doi.org/10.54694/stat.2024.50

Abstract
Inflation expectations play an important role in the transmission mechanism of inflation targeting in the context of the length and costs of the disinflationary process. The objective of our paper is to employ econometric analysis to verify whether financial analysts’ and corporate managers’ inflation expectations in Czechia (from Q3 1999 to Q2 2024) show basic features of rational expectations and what impact the past YoY CPI inflation rate, the CNB’s inflation forecast and the CNB’s inflation target have on their expectations. We find that the formation of financial analysts’ and corporate managers’ yearly inflation expectations with time horizons of one year and three years differs considerably. For corporate managers’ inflation expectations, adaptive reasoning plays a more important role. Financial analysts take more account of the CNB’s one-year inflation forecasts in forming their yearly expectations, while the inflation target, as an explanatory variable, is statistically significant only for their three-year inflation expectations. Neither group of respondents meets the required criteria for rational expectations in terms of the tests formulated by Pesaran (1987), and Fama (1965 and 1970). In particular, their yearly inflation expectations exhibit systematic errors. Surprisingly, the time series of financial analysts’ inflation expectations contain a seasonal component.

Keywords
Inflation expectations, monetary policy, inflation targeting, Czech National Bank

Statistika, 105(1): 33–48
https://doi.org/10.54694/stat.2024.33

Abstract
The paper explores new statistical approaches for studying links between cross-border financial flows and the exchange rate. The paper first discusses limitations of the balance of payments statistics in analysing foreign exchange market imbalances by explaining the methodological principles that drive a wedge between balance of payments transactions and cross-border flows. Then it continues with a discussion on the analytical potential of the so-called monetary presentation of the balance payments. Visual analysis tentatively suggests that in the case of the CZK/EUR currency pair, net external flows (an aggregate identified by the monetary presentation) can explain reasonably well past exchange rate developments, if adjusted for central bank intervention.

Keywords
Balance of payments, monetary presentation, monetary aggregates, foreign exchange

Statistika, 105(1): 49–64
https://doi.org/10.54694/stat.2024.40

Abstract
Pension systems are sensitive to economic and demographic challenges. The sustainability sub-index is essential for ensuring the stability and reliability of pension systems for both current and future pensioners. It assists policymakers and stakeholders in identifying areas where reforms may be necessary to enhance the sustainability of pension policies. This contribution focuses on determining the weights for individual indicators of the sustainability sub-index using several methods of weight determination in multi-criteria decision-making, specifically subjective methods. The weights are determined using four methods: Saaty’s exact and approximate method, Thurstone's method of pair comparison, and Best-Worst method. It also provides sustainability sub-index values for selected European countries included in Mercer’s score determination, as well as for Slovakia, which is not yet included in Mercer’s evaluations. Thurstone's method of pair comparison appears to be the method most consistent with Mercer's methodology in determining the weights for indicators of the sustainability sub-index.

Keywords
Sustainability, indicators, weights, Saaty’s method, Best-Worst method, Thurstone's method of pair comparison

Statistika, 105(1): 65–86
https://doi.org/10.54694/stat.2024.26

Abstract
Tertiary level of health care should provide highly specialized health services, that include the most complex methods and procedures of diagnosis, treatment and rehabilitation. The aim of the research is to examine the impact of the quality of health services on user satisfaction of medical services at the tertiary level of health care. For the purposes of this research, clinical centers of the tertiary health care level operating in the territory of Bosnia and Herzegovina were selected, which also represents the basic set of research. The survey was conducted on a sample of 1 022 users of health services provided by clinical centers in the territory of Bosnia and Herzegovina, where the cities represented the strata in the research: Sarajevo, Banja Luka, Tuzla, Mostar and Foča. The results indicate a strong influence of independent constructs on dependent constructs, that is, the quality of health services has a strong influence on the level of user satisfaction with (non)medical services.

Keywords
Quality of health services, user satisfaction, tertiary level of health care, structural equation modeling

Statistika, 105(1): 87–101
https://doi.org/10.54694/stat.2024.32

Abstract
Our paper is based on the five principal dimensions of the International Digital Economy and Society Index (I-DESI), but instead of using the original scoring model based on arbitrary pre-determined weights, we apply more objective ranking methods that use the statistical properties of the data series to determine where the Visegrad Group (V4) countries (Czechia, Hungary, Poland and Slovakia) stand in terms of digital development among the countries of the European Union and other developed countries in the data set. The ranking is performed using the DEA-CWA (Data Envelopment Analysis/Common Weights Analysis) method (with six models) and the TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) method. Although the resulting weight vectors differ significantly from the arbitrary weights set by the European Commission, the country rankings remain similar, displaying relatively little sensitivity to the weighting method chosen.

Keywords
Data Envelopment Analysis, information and communication technology, International Digital Economy and Society Index, TOPSIS, Visegrád Group

Statistika, 105(1): 102–122
https://doi.org/10.54694/stat.2024.18

Abstract
The Indian labour market exhibits significant gender wage disparities, particularly among regular/salaried employees and casual workers. To study these disparities comprehensively, we present a dual-methodological approach by combining Quantile Regression (QR) and Melly-Machado-Mata (MMM) decomposition. Using secondary data from India's Periodic Labour Force Survey (PLFS) 2020–21, the study highlights the intricate interplay of various demographic, personal, and occupational characteristics on wage distributions. The findings highlight the persistence of the gender wage gap across different quantile levels for both employment types. The decomposition results reveal that discrimination significantly contributes to the wage gap, particularly at lower income levels, indicating a "sticky floor" effect for regular/salaried employees. Conversely, casual workers face a consistent wage gap across all quantiles, with discrimination remaining a crucial factor. This research highlights the robustness and precision of QR modelling and decomposition, providing a comprehensive framework for scientifically assessing the gender-based wage gap and exploring policy interventions to address these inequalities.

Keywords
Quantile regression, decomposition, Oaxaca-Blinder, Melly-Machado-Mata, PLFS

Statistika, 105(1): 123–130
https://doi.org/10.54694/stat.2024.38

Abstract
Household Finance and Consumption Survey (HFCS) is a survey focused mainly on mapping financial and assets situation of households. In Czechia, the survey has been conducted annually since 2020 under the name Finanční situace domácností (FSD). The article focuses on the implementation of the survey in the Czech setting, mainly describing the cooperation between the Czech Statistical Office and the Czech National Bank. A particular attention is paid to the methodological aspect of FSD as well as to the survey’s main outcomes, primarily the net wealth indicator. The integration of FSD into the EU-SILC (European Union – Statistics on Income and Living Conditions) survey enables annual data collection and publication of main results, as well as the reduction of respondent burden.

Keywords
Household Finance and Consumption Survey (HFCS), net wealth, household survey, EU-SILC