TY  - JOUR
AU  - Cameron,A. Colin
AU  - Gelbach,Jonah B.
AU  - Miller,Douglas L.
TI  - Bootstrap-Based Improvements for Inference with Clustered Errors
JF  - National Bureau of Economic Research Technical Working Paper Series
VL  - No. 344
PY  - 2007
Y2  - September 2007
UR  - http://www.nber.org/papers/t0344
L1  - http://www.nber.org/papers/t0344.pdf
N1  - Author contact info:
A. Colin Cameron
Department of Economics
UC Davis
One Shields Avenue
Davis, CA 95616
E-Mail: accameron@ucdavis.edu

Jonah Gelbach
Yale Law School Class of 2013 and
Senior Research Fellow, Program in Applied Economi
Yale University
New Haven, CT
Tel: 510/643-0791
Fax: 510/643-8614
E-Mail: gelbach@gmail.com

Douglas L. Miller
Department of Economics
University of California, Davis
One Shields Avenue
Davis, CA 95616-8578
Tel: 530/752-8490
E-Mail: dlmiller@ucdavis.edu
AB  - Researchers have increasingly realized the need to account for within-group dependence in estimating standard errors of regression parameter estimates.  The usual solution is to calculate cluster-robust standard errors that permit heteroskedasticity and within-cluster error correlation, but presume that the number of clusters is large. Standard asymptotic tests can over-reject, however, with few (5-30) clusters. We investigate inference using cluster bootstrap-t procedures that provide asymptotic refinement.  These procedures are evaluated using Monte Carlos, including the example of Bertrand, Duflo and Mullainathan (2004). Rejection rates of ten percent using standard methods can be reduced to the nominal size of five percent using our methods.
ER  -