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

被引：29

作者：

Baltagi, Badi H. ^{[1
]}

Bresson, Georges

Pirotte, Alain

机构：

[1] Syracuse Univ, Dept Econ, Syracuse, NY 13244 USA

[2] Syracuse Univ, Ctr Policy Res, Syracuse, NY 13244 USA

[3] Univ Pantheon Assas Paris 2, ERMES, CNRS, F-75230 Paris 05, France

来源：

JOURNAL OF ECONOMETRICS | 2006年 / 134卷 / 02期

关键词：

panel data; heteroskedasticity; Lagrange multiplier tests; error components; Monte Carlo simulations;

D O I：

10.1016/j.jeconom.2005.06.029

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

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. (c) 2005 Elsevier B.V. All rights reserved.

引用

页码：401 / 417

页数：17

共 21 条

[1]

[Anonymous], ECONOMETRIC REV

[2] A GENERALIZED ERROR COMPONENT MODEL WITH HETEROSCEDASTIC DISTURBANCES [J].