Heteroskedasticity in Fixed-Effects One-Way Error Component Models: Evaluating the Performance of Standard Tests

28 Pages Posted: 2 Mar 2009 Last revised: 7 Jun 2012

Carolina Castilla

Colgate University - Department of Economics

Date Written: September 1, 2008

Abstract

This paper evaluates the performance of the Breusch-Pagan LM test and the White test for heteroskedasticity in fixed-effects one-way error components models. It contrasts the behavior of these tests under the fixed-effects model with the first differences model for different variance functional forms, degrees of heteroskedasticity and sample sizes. Monte Carlo results indicate both tests perform equally well in large samples. They are very sensitive to overall sample size, as changes in T or N do not affect the performance if overall sample size is held constant. The White test seems to be more reliable for identifying heteroskedasticity than the Breusch-Pagan test, even if we are able to identify the actual functional form of the variance. The performance of either test in small samples is poor.

Keywords: Heteroskedasticity, Fixed-Effects, Panel Error Component Models

JEL Classification: C12, C23

Suggested Citation

Castilla, Carolina, Heteroskedasticity in Fixed-Effects One-Way Error Component Models: Evaluating the Performance of Standard Tests (September 1, 2008). Available at SSRN: https://ssrn.com/abstract=1351063 or http://dx.doi.org/10.2139/ssrn.1351063

Carolina Castilla (Contact Author)

Colgate University - Department of Economics ( email )

13 Oak Drive
Hamilton, NY 13346
United States

Paper statistics

Downloads
230
Rank
108,869
Abstract Views
1,469