The Finite-Sample Performance of White's Test for Heteroskedasticity Under Stochastic Regressors

Abstract

We study the finite-sample properties of White's test for heteroskedasticity in stochastic regression models where explanatory variables are random and not given. We investigate by simulation the effect of non independence of explanatory variables and error term and heteroskedasticity on White's test. A standard bootstrap method in the computationally convenient form is found to work well with respect to the size and power.

Keywords:

• Heteroskedasticity
• Non independence of explanatory variables and error term
• White's test

Mathematics Subject Classification:

• Primary 62J05
• Secondary 62P20

Acknowledgment

The authors thank helpful comments by an anonymous referee. Masakazu Ando is financially supported for this work by Grant-in-Aid for Scientific Research (KAKENHI(16.12163)).

Notes

¹We remark the heteroskedasticity consistent covariance matrix estimators such as HC1, HC2, HC3, and HC4 (cf., e.g., Hodoshima and Ando, 2006) do not work for White's test for heteroskedasticity since they do not satisfy the condition (cf., the proof of Theorem 2 of White, 1980) when is replaced by the heteroskedasticity consistent covariance matrix estimators.