Measuring Changes in Corruption over Time * Preliminary version: This paper is under active development. Conclusions, arguments, and evidence may change as research progresses. Maya Dalton 1 and Justin Esarey 2 1 Pennsylvania State University, Department of Political Science 2 Wake Forest University, Department of Politics and International Affairs July 3, 2023 Abstract Although the most commonly used quantitative measures of corruption are highly correlated, we find that these measures do not accurately track changes in corruption within a given country over time. Many causal inference research designs, such as difference-in-difference designs, rely on such within-country changes to identify causal relationships. As a result, we argue that findings based on changes in corruption within countries should be interpreted with caution. We show that factor scores extracting the common signal from multiple measures should be preferred to any single measure of corruption when studying changes within a country over time. * We gratefully acknowledge financial support for this project provided by the Wake Forest University Undergraduate Research and Creative Activities Center (URECA) and the WFU Department of Politics and International Affairs.
Measuring Changes in Corruption over Time
Jul 06, 2023
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Related Documents
