Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/149090
Authors: 
MacKinnon, James G.
Webb, Matthew D.
Year of Publication: 
2016
Series/Report no.: 
Queen's Economics Department Working Paper 1364
Abstract: 
Inference based on cluster-robust standard errors is known to fail when the number of clusters is small, and the wild cluster bootstrap fails dramatically when the number of treated clusters is very small. We propose a family of new procedures called the sub- cluster wild bootstrap. In the case of pure treatment models, where all the observations in each cluster are either treated or not, the new procedures can work astonishingly well. The key requirement is that the sizes of the treated and untreated clusters should be very similar. Unfortunately, the analog of this requirement is not likely to hold for difference-in-differences regressions. Our theoretical results are supported by extensive simulations and an empirical example.
Subjects: 
CRVE
grouped data
clustered data
wild bootstrap
wild cluster bootstrap
subclustering
treatment model
difference-in-differences
robust inference
JEL: 
C15
C21
C23
Document Type: 
Working Paper

Files in This Item:
File
Size
556.76 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.