Heteroskedasticity-Robust Inference in Finite Samples

By Jerry A. Hausman, C. Palmer. 2012

47 citations recorded by the source corpus.

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 expansion of the test statistic distribution. Our preferred test outperforms existing methods in both size and power for low, moderate, and severe levels of heteroskedasticity.

Subfields: Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/3d8c435eb89391a35273d319c232f23e0a9375c4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Resurrecting weighted least squares (2017, unknown): “As an alternative to bootstrapping, one can consider higherorder accuracy by using Edgeworth expansions, as studied in Hausman and Palmer (2012).”
Robust Standard Errors in Small Samples: Some Practical Advice (2016, methodology): “Some of these alternatives focus on reducing the bias of the variance estimators (MacKinnon & White, 1985), some exploit higher-order expansions (Hausman & Palmer, 2011), others attempt to improve their properties by using resampling methods (Davidson & Flachaire, 2008; Cameron, Gelbach, & Miller,…”