NATIONAL BUREAU OF ECONOMIC RESEARCH
NATIONAL BUREAU OF ECONOMIC RESEARCH

Heteroskedasticity-Robust Inference in Finite Samples

Jerry A. Hausman, Christopher J. Palmer

NBER Working Paper No. 17698
Issued in December 2011
NBER Program(s):   TWP

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.

download in pdf format
   (283 K)

email paper

This paper is available as PDF (283 K) or via email.

Machine-readable bibliographic record - MARC, RIS, BibTeX

Document Object Identifier (DOI): 10.3386/w17698

Published: Economics Letters, Volume 116, Issue 2, August 2012, Pages 232­-235 citation courtesy of

Users who downloaded this paper also downloaded these:
Bremus, Buch, Russ, and Schnitzer w19093 Big Banks and Macroeconomic Outcomes: Theory and Cross-Country Evidence of Granularity
Andreoni and Rao w16373 The Power of Asking: How Communication Affects Selfishness, Empathy, and Altruism
Imbens and Kolesar w18478 Robust Standard Errors in Small Samples: Some Practical Advice
McInish and Wood Competition, Fragmentation, and Market Quality
Stock and Watson t0323 Heteroskedasticity-Robust Standard Errors for Fixed Effects Panel Data Regression
 
Publications
Activities
Meetings
NBER Videos
Data
People
About

Support
National Bureau of Economic Research, 1050 Massachusetts Ave., Cambridge, MA 02138; 617-868-3900; email: info@nber.org

Contact Us