Testing inference in heteroskedastic linear regressions: a comparison of two alternative approaches. Issue 8 (24th May 2019)

• Record Type: Journal Article
• Authors: Cribari-Neto, Francisco; Pereira, Inara F. S.
• Is Part Of: Journal of statistical computation and simulation. Volume 89:Issue 8(2019)
• Page Start: 1437
• Page End: 1465
• Publication Date: 2019-05-24
• Subjects: Box-Cox transformation -- generalized least squares -- heteroskedasticity -- linear regression -- ordinary least squares -- quasi-t test -- z test; 62J05; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5028505
• DOI: 10.1080/00949655.2019.1586902
• Languages: English
• ISSNs: 0094-9655

Abstract

Abstract : We consider the issue of performing testing inferences on the parameters that index the linear regression model under heteroskedasticity of unknown form. Quasi- t test statistics use asymptotically correct standard errors obtained from heteroskedasticity-consistent covariance matrix estimators. An alternative approach involves making an assumption about the functional form of the response variances and jointly modelling mean and dispersion effects. In this paper we compare the accuracy of testing inferences made using the two approaches. We consider several different quasi- t tests and also z tests performed after estimated generalized least squares estimation which was carried out using three different estimation strategies. The numerical evidence shows that some quasi- t tests are typically considerably less size distorted in small samples than the tests carried out after the jointly modelling of mean and dispersion effects. Finally, we present and discuss two empirical applications.