Transition choice probabilities and welfare analysis in additive random utility models (Q2431096)

The authors study consequences of attributes changes in additive random utility models. They derive expressions for the transition choice probabilities associated to these changes. A closed-form formula is obtained for the logit. The authors use these expressions to compute the cumulative distribution functions of the compensating variation (CV) conditional choices. The unconditional distribution is also provided. The conditional moments of the CV are obtained as a one-dimensional integral of the transition choice probabilities. This framework allows us to derive a stochastic version of Shephard's lemma, which relates the expected conditional CV and the transition choice probabilities. CV is computed for a simple binary linear in income choice model. There are shown that the information on the transitions leads to better estimates of the CV than those obtained when only information on individual choices is used. For the case of income logit, the authors compute the conditional distribution of CV, which generalizes the logsum formula. Finally, there is derived a new welfare formula for the disaggregated version of the representative consumer CES model.