SELECTION BIAS CORRECTIONS BASED ON THE MULTINOMIAL LOGIT MODEL: MONTE CARLO COMPARISONS

This survey presents the set of methods available in the literature on selection bias correction, when selection is specified as a multinomial logit model. It contrasts the underlying assumptions made by the different methods and shows results from a set of Monte Carlo experiments. We find that, in many cases, the approach initiated by <link rid="b2">Dubin and MacFadden (1984)</link> as well as the semi-parametric alternative recently proposed by <link rid="b1">Dahl (2002)</link> are to be preferred to the most commonly used <link rid="b5">Lee (1983)</link> method. We also find that a restriction imposed in the original Dubin and MacFadden paper can be waived to achieve more robust estimators. Monte Carlo experiments also show that selection bias correction based on the multinomial logit model can provide fairly good correction for the outcome equation, even when the IIA hypothesis is violated. Copyright 2007 The Author Journal compilation © 2007 Blackwell Publishing Ltd.