TY  - JOUR
AU  - Hausman,Jerry A.
AU  - Palmer,Christopher J.
TI  - Heteroskedasticity-Robust Inference in Finite Samples
JF  - National Bureau of Economic Research Working Paper Series
VL  - No. 17698
PY  - 2011
Y2  - December 2011
UR  - http://www.nber.org/papers/w17698
L1  - http://www.nber.org/papers/w17698.pdf
N1  - Author contact info:
Jerry A. Hausman
Department of Economics
MIT, Room E52-271A
50 Memorial Drive
Cambridge, MA  02139
Tel: 617/253-3644
Fax: 617/253-1330
E-Mail: jhausman@mit.edu

Christopher Palmer
Department of Economics
MIT, Room E52-391
50 Memorial Drive
Cambridge, MA 02142
Tel: 617-299-6511
E-Mail: cjpalmer@mit.edu
AB  - Since the advent of heteroskedasticity-robust standard errors, several papers have proposed adjustments to the original White formulation. We replicate earlier findings that each of these adjusted estimators performs quite poorly in finite samples. We propose a class of alternative heteroskedasticity-robust tests of linear hypotheses based on an Edgeworth expansions of the test statistic distribution. Our preferred test outperforms existing methods in both size and power for low, moderate, and severe levels of heteroskedasticity.
ER  -