Thesis PDFs, slides, figures and analysis code for "Markups and Public Procurement: Evidence from Czech Construction Tenders." The latest materials are on marek-chadim.github.io.
MScThesis.pdf,MScSlides.pdf— MSc thesis (Stockholm School of Economics, 2024) and defense slidesBScThesis.pdf— BSc thesis (Charles University, 2023)MarkupsProcurement/— MSc thesis analysis: R and Stata code, data preparation, and the outputs it produces (descriptive statistics, selection-on-observables designs, models for unobserved factors)figures/— exported thesis figures
MSc thesis, Stockholm School of Economics (2024). DOI: hhs.primo.exlibrisgroup.com
Abstract. This paper analyzes the effect of public procurement on firm markups, using a panel dataset of Czech construction firms from 2006 to 2021. Markups are estimated through a structural framework, while biases are addressed using a selection on observables design and models for unobserved factors. Propensity score-based estimations indicate that firm markups increase by approximately 15% during contract years. A temporal analysis, employing synthetic control and matrix completion methods, reveals that treatment effects decline from around 30% in 2006 to 10% in 2021. These patterns are consistent with institutional improvements in the Czech Republic and offer empirical evidence of increasing efficiency in public spending.
Bachelor's thesis, Charles University in Prague (2023). DOI: dspace.cuni.cz
For my undergraduate thesis, I estimated production functions for firms in the Czech construction sector, addressing endogeneity in productivity shocks and variable input usage using the control function approach and GMM. A key contribution of this work was the creation of a novel dataset as well as the structural inference of the markup distribution.
- De Loecker & Warzynski (2012), Markups and Firm-Level Export Status
- De Loecker, Eeckhout & Unger (2020), The Rise of Market Power and the Macroeconomic Implications
- Imbens & Xu (2024), LaLonde (1986) after Nearly Four Decades: Lessons Learned
- Arkhangelsky & Imbens (2024), Causal Models for Longitudinal and Panel Data: A Survey