It is a common finding in empirical discrete choice studies that the estimated mean relative values of the coefficients (i.e. WTP's) from multinomial logit (MNL) estimations differ from those calculated using mixed logit estimations, where the mixed logit has the better statistical fit. However,...

An emerging quantitative spatial economics literature models commuting interactions by a gravity equation that is mathematically equivalent to a multinomial logit model. This model is widely viewed as restrictive because of the independence of irrelevant alternatives (IIA) property that links...

This paper shows that Hausman-McFadden and related tests for the multinomial logit model are not informative about failure of IIA, but only about specification error in the deterministic part of the utilities attached to choice alternatives. It is shown that the multinomial logit cannot be...

This paper studies inter- and intramodal competition in the London-Paris passenger market. Using revealed preference data, we estimate nested and mixed multinomial logit models to examine passenger behaviour in the London-Paris market. We present a case study on the relocation of Eurostar...

In a binary logit analysis with unequal sample frequencies of the twooutcomes the less frequent outcome always has lower estimatedprediction probabilities than the other one. This effect is unavoidable,and its extent varies inversely with the fit of the model, as given by anew measure that...

In this paper a model, based on the nested multinomial logit model, is used to analyze airport competition and airline competition in a multiple airport region. It is shown that if the frequency elasticity of demand is smaller than 1, airfare-frequency and airport tax equilibria exist and are...

In binary discrete regression models like logit or probit the omis-sion of a relevant regressor (even if it is orthogonal) depresses the re-maining b coefficients towards zero. For the probit model, Wooldridge(2002) has shown that this bias does not carry over to the effect ofthe regressor on...

In a discrete model, the predicted probabilities of a particular eventcan be matched to the observed (0, I) outcomes and this will give riseto a measure of fit for that event. Previous results for the binomialmodel are applied to multinomial models. In these models the measureof fit will vary...