Simulation Analyse Of Ordered Discrete Choice Models

The main content of this paper is using a variety of Monte Carlo experiments to analyse the performance of the stastistics suggested in Mora and Moro-Egido (2008). In that paper, how to test the specification of an ordered discrete choice model against a general alternative is discussed. Two main approaches can be followed: tests based on moment conditions and tests based on comparisons between parametric and nonparametric estimations. Following these approaches, various statistics are proposed and their asymptotic properties are discussed. In this paper, the performance of the statistics is compared by means of simulations. An variant of the moment–based statistic yields the best results in models with a single explanatory variable. In models with various explanatory variables the results are less conclusive, since the relative performance of the statistics depends on both the fit of the model and the type of misspecification that is considered.