QED Working Paper Number
1383

We study asymptotic inference based on cluster-robust variance estimators for regression models with clustered errors, focusing on the wild cluster bootstrap and the ordinary wild bootstrap. We state conditions under which both asymptotic and bootstrap tests and confidence intervals will be asymptotically valid. These conditions put limits on the rates at which the cluster sizes can increase as the number of clusters tends to infinity. To include power in the analysis, we allow the data to be generated under sequences of local alternatives. Simulation experiments illustrate the theoretical results and show that all methods can work poorly in certain cases.

JEL Codes
C15
C21
C23
Keywords
clustered data
cluster-robust variance estimator
CRVE
inference
wild bootstrap
wild cluster bootstrap
Working Paper