Joint LM test for homoskedasticity in a one-way error component model

Badi H. Baltagi, Georges Bresson, Alain Pirotte

Research output: Contribution to journalArticle

28 Scopus citations

Abstract

This paper considers a general heteroskedastic error component model using panel data, and derives a joint Lagrange multiplier (LM) test for homoskedasticity against the alternative of heteroskedasticity in both error components. It contrasts this joint LM test with marginal LM tests that ignore the heteroskedasticity in one of the error components. Monte Carlo results show that misleading inference can occur when using marginal rather than joint tests when heteroskedasticity is present in both components.

Original languageEnglish (US)
Pages (from-to)401-417
Number of pages17
JournalJournal of Econometrics
Volume134
Issue number2
DOIs
StatePublished - Oct 1 2006

Keywords

  • Error components
  • Heteroskedasticity
  • Lagrange multiplier tests
  • Monte Carlo simulations
  • Panel data

ASJC Scopus subject areas

  • Economics and Econometrics

Fingerprint Dive into the research topics of 'Joint LM test for homoskedasticity in a one-way error component model'. Together they form a unique fingerprint.

  • Cite this