What's Logs Got to do With it: On the Perils of log Dependent Variables and Difference-in-Differences

2023/07/31 by Brendon McConnell, McConnell, Brendon · 1 citation
Economics, Econometrics and Finance · #Econometrics (econ.EM) #FOS: Economics and business #Spatial and Panel Data Analysis

paper · pdf · doi:10.48550/arxiv.2308.00167

openalex publication_date 2023/07/31 · openalex created_date 2023/08/03 · openalex updated_date 2026/07/28

Abstract

The log transformation of the dependent variable is not innocuous when using a difference-in-differences (DD) model. With a dependent variable in logs, the DD term captures an approximation of the proportional difference in growth rates across groups. As I show with both simulations and two empirical examples, if the baseline outcome distributions are sufficiently different across groups, the DD parameter for a log-specification can be different in sign to that of a levels-specification. I provide a condition, based on (i) the aggregate time effect, and (ii) the difference in relative baseline outcome means, for when the sign-switch will occur.

Cited by

• Black and Latinx workers reap lower rewards than White workers from years spent working in big cities

Related

• Generalizing Difference-in-Differences to Non-Canonical Settings: Identifying an Array of Estimands
• Factorial Difference-in-Differences
• Factorial Difference-in-Differences
• Logs with Zeros? Some Problems and Solutions
• Logs with zeros? Some problems and solutions