Título: Tests for unbalanced error component models under local misspecication
Autores: Sosa Escudero, Walter
Bera, Anil K.
Fecha: 2010-06-10
2008
Publicador: Unversidad Nacional de La Plata
Fuente:


Tipo: Articulo
Documento de trabajo
Tema: error components model; unbalanced panel data; testing; misspecification
Economía
Modelos econométricos
Econometría
Descripción: This paper derives unbalanced versions of the tests statistics for first order serial correlation and random individual e®ects summarized in Sosa Escudero and Bera (2001), and updates their xttest1 routine. The derived tests statistics should be useful for applied researchers faced with the increasing availability of panel information where not every individual or country is observed for the full time span. Also, as it was the case of the previously available tests, the test statistics proposed here are based on the OLS residuals, and hence are computationally very simple.
Trabajo publicado en <i>The Stata Journal</i>, Volume 8, Number 1, pp. 68-78.
Idioma: Inglés