Publication Type

Working Paper

Version

publishedVersion

Publication Date

10-2010

Abstract

The robustness of the LM tests for spatial error dependence of Burridge (1980) for the linear regression model and Anselin (1988) for the panel regression model are examined. While both tests are asymptotic ally robust against distributional misspecification, their finite sample behavior can be sensitive to the spatial layout. To overcome this shortcoming, standardized LM tests are suggested. Monte Carlo results show that the new tests possess good finite sample properties. An important observation made throughout this study is that the LM tests for spatial dependence need to be both mean- and variance-adjusted for good finite sample performance to be achieved. The former is, however, often neglected in the literature.

Keywords

Distributional misspecification, Group interaction, LM test, Moran’s ITest, Robustness, Spatial panel models

Discipline

Econometrics

Research Areas

Econometrics

First Page

1

Last Page

25

Publisher

SMU Economics and Statistics Working Paper Series, No. 11-2010

City or Country

Singapore

Embargo Period

1-2-2017

Copyright Owner and License

Authors

Comments

Published in Econometrics Journal, https://doi.org/10.1111/j.1368-423X.2012.00385.x

Included in

Econometrics Commons

Share

COinS