Person:

Jaeger, Simon

This dissertation consists of three independent essays in labor and public economics. Chapter 1 presents evidence on how exogenous worker exits affect a firm’s demand for incumbent workers and new hires. Using matched employer-employee data based on the universe of German social security records, I analyze the effects of unexpected worker deaths and show that these worker exits affect the remaining workers’ wages and retention probabilities. Chapter 2 (with Peter Ganong) proposes a permutation test for the Regression Kink (RK) design. As a complement to standard RK inference, we propose that researchers construct a distribution of placebo estimates in regions with and without a policy kink and use this distribution to gauge statistical significance of RK estimates. Chapter 3 (with Johannes Abeler) analyzes a laboratory experiment to study how tax complexity affects the reaction to tax changes.

The Regression Kink (RK) design is an increasingly popular empirical method, with more than 20 studies circulated using RK in the last 5 years since the initial circulation of Card, Lee, Pei and Weber (2012). We document empirically that these estimates, which typically use local linear regression, are highly sensitive to curvature in the underlying relationship between the outcome and the assignment variable. As an alternative inference procedure, motivated by randomization inference, we propose that researchers construct a distribution of placebo estimates in regions without a policy kink. We apply our procedure to three empirical RK applications – two administrative UI datasets with true policy kinks and the 1980 Census, which has no policy kinks – and we find that statistical significance based on conventional p-values may be spurious. In contrast, our permutation test reinforces the asymptotic inference results of a recent Regression Discontinuity study and a Difference-in-Difference study. Finally, we propose estimating RK models with a modified cubic splines framework and test the performance of different estimators in a simulation exercise. Cubic specifications – in particular recently proposed robust estimators (Calonico, Cattaneo and Titiunik 2014) – yield short interval lengths with good coverage rates.