A NOTE ON SPURIOUS REGRESSION IN PANELS WITH CROSS-SECTION DEPENDENCE
No hay miniatura disponible
Fecha
Autores
Título de la revista
ISSN de la revista
Título del volumen
Editor
Resumen
Descripción
This paper analyses regression of two independent stationary panels with cross-sectional dependence. It is shown that the pooling least squares (PLS) estimator converges to zero in probability while the individual OLS estimator converges to a random variable. However, the PLS-based and the OLS-based t-statistics diverge, so the null hypothesis of no correlation tends to be spuriously rejected.