Hostname: page-component-77c89778f8-n9wrp Total loading time: 0 Render date: 2024-07-17T02:30:45.506Z Has data issue: false hasContentIssue false
  • English
  • Français

AN ALTERNATIVE DERIVATION OF MUNDLAK'S FIXED EFFECTS RESULTS USING SYSTEM ESTIMATION

Published online by Cambridge University Press:  03 November 2006

Badi H. Baltagi
Badi H. Baltagi
Affiliation:
Syracuse University
Get access Rights & Permissions [Opens in a new window]

Abstract

Mundlak (1978, Econometrica 46, 69–85) showed that the fixed effects estimator can be obtained as generalized least squares (GLS) for a panel regression model where the individual effects are random but are all hopelessly correlated with the regressors. This result was obtained by partitioned inversion after substituting the reduced form expression for the individual effects as a function of the means of all the regressors. This note shows that Mundlak's result can be obtained using system estimation without using partitioned inversion. System estimation has proved useful for deriving two-stage least squares (2SLS) and three-stage least squares (3SLS) counterparts for the random effects panel models by Baltagi (1981, Journal of Econometrics 17, 189–200). It also has been used for obtaining an alternative derivation of the Hausman tests that is robust to heteroskedasticity of unknown form (see Arellano, 1993, Journal of Econometrics 59, 87–97) and more recently, for obtaining generalized method of moments (GMM) estimators for dynamic panel models (see Arellano and Bover, 1995, Journal of Econometrics 68, 29–51; and Blundell and Bond, 1998, Journal of Econometrics 87, 115–143, to mention a few). We also show that a necessary and sufficient condition for ordinary least squares (OLS) to be equivalent to GLS is satisfied for this model.

Type
NOTES AND PROBLEMS
Information
Econometric Theory , Volume 22 , Issue 6 , December 2006 , pp. 1191 - 1194
Copyright
© 2006 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Arellano, M. (1993) On the testing of correlated effects with panel data. Journal of Econometrics 59, 87–97.CrossRefGoogle Scholar
Arellano, M. & O. Bover (1995) Another look at the instrumental variables estimation of error-component models. Journal of Econometrics 68, 29–51.CrossRefGoogle Scholar
Baltagi, B.H. (1981) Simultaneous equations with error components. Journal of Econometrics 17, 189–200.CrossRefGoogle Scholar
Blundell, R. & S. Bond (1998) Initial conditions and moment restrictions in dynamic panel data models. Journal of Econometrics 87, 115–143.CrossRefGoogle Scholar
Hausman, J.A. (1978) Specification tests in econometrics. Econometrica 46, 1251–1271.CrossRefGoogle Scholar
Mundlak, Y. (1978) On the pooling of time series and cross-section data. Econometrica 46, 69–85.CrossRefGoogle Scholar
Zyskind, G. (1967) On canonical forms, non-negative covariance matrices and best and simple least squares linear estimators in linear models. Annals of Mathematical Statistics 36, 1092–1109.CrossRefGoogle Scholar