Public expenditure on tertiary education and over-qualification risk

This research dataset and accompanying R files support the empirical analysis conducted for the study “Public Expenditure on Tertiary Education and Over-Qualification Risk: A DEA-Based Study of Education-to-Employment Efficiency in European Countries”. The dataset contains a balanced panel of 29 European countries for the period 2013–2023, covering 319 country-year observations. It combines indicators from Eurostat and World Bank Open Data related to public expenditure on tertiary education, over-qualification, educational matching, unemployment, unemployment among individuals with advanced education, R&D expenditure, tertiary graduates, lifelong learning participation and population. The dataset was prepared to evaluate how efficiently European countries transform public expenditure on tertiary education into lower over-qualification and stronger education-to-employment matching. The educational matching rate was calculated as 100 minus the over-qualification rate and used as the desirable output in the data envelopment analysis. Public expenditure on tertiary education, expressed as a percentage of GNI, was used as the input variable. Missing values were treated using country-specific time-series interpolation or extrapolation procedures, and all imputed observations were documented to ensure transparency and reproducibility. The deposited files include the cleaned analytical dataset, the RData file containing the prepared objects used in the analysis, and R scripts for data preparation, descriptive statistics, DEA estimation, CRS robustness testing, VRS–CRS comparison, second-stage regression analysis, fractional logit estimation and lagged robustness checks. The materials allow users to reproduce the main empirical results, including the calculation of DEA efficiency scores, country-level rankings, robustness models and regression outputs. The dataset may be useful for researchers studying public finance, higher education expenditure, over-qualification, labour-market mismatch, human capital efficiency and cross-country education-to-employment outcomes in Europe.