Research Paper Banca d'Italia Temi di discussione 705
The (mis)specification of discrete time duration models with unobserved heterogeneity: a Monte Carlo study
07 Mar 2009
The most popular statistical models among empirical researchers are usually the ones which can be easily estimated by using commonly available software packages. Sequential binary models with or without normal random effects are an example of such models, because they can be adopted to estimate discrete time duration models in presence of unobserved heterogeneity.
But an easy-to-implement estimation may incur a cost. In this paper we use Monte Carlo methods to analyze the consequences of omission or misspecification of unobserved heterogeneity in single spell discrete time duration models.