Reference : A full heteroscedastic one-way error components model: Pseudo-maximum likelihood esti...
Parts of books : Contribution to collective works
Business & economic sciences : Quantitative methods in economics & management
A full heteroscedastic one-way error components model: Pseudo-maximum likelihood estimation and specification testing
Lejeune, Bernard[Université de Liège - ULg > HEC - Ecole de gestion de l'ULg > Economie politique et microéconomie appliquée >]
Panel Data Econometrics: Theoretical Contributions and Empirical Applications
Baltagi, Badi H.
Contributions to economic analysis
[en] Error components model ; Heteroscedasticity ; Pseudo-maximum likelihood estimation and m-testing
[en] This paper proposes an extension of the standard one-way error components model allowing for heteroscedasticity in both the individual-specific and the general error terms, as well as for unbalanced panel. On the grounds of its computational convenience, its potential efficiency, its robustness to non-normality and its robustness to possible misspecification of the assumed scedastic structure of the data, we argue for estimating this model by Gaussian pseudo-maximum likelihood of order two. Further, we review how, taking advantage of the powerful m-testing framework, the correct specification of the prominent aspects of the model may be tested. We survey potentially useful nested, non-nested, Hausman and information matrix type diagnostic tests of both the mean and the variance specification of the model. Finally, we illustrate the usefulness of our proposed model and estimation and diagnostic testing procedures through an empirical example.