Discrete choice models with multiplicative error terms

132 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Can scale and coefficient heterogeneity be separated in random coefficients models? (2012, methodology): “Other work concerned with scale includes the multiplicative error model of Fosgerau and Bierlaire (2009), but this is based on a non-random scale parameter.”
New SP-values of time and reliability for freight transport in the Netherlands (2014, methodology): “…C = transport cost T = transport time = standard deviation of the transport time distribution e = disturbance term (i.i.d, extreme value type I) The second specification that we tried was the multinomial logit model in logwillingness-to-pay (logWTP) space (Fosgerau and Bierlaire, 2009).”
Unconstrained weibit stochastic user equilibrium model with extensions (2014, methodology): “According to Fosgerau and Bierlaire (2009), the MNW model can be posed as a random utility model with multiplicative error terms: U r 1⁄4 g r f ij bij e r ; 8r 2 Rij; ij 2 IJ; ð47Þ where e r is the weibull distributed random error term.”
The multinomial logit model revisited: A semi-parametric approach in discrete choice analysis (2011, methodology): “Furthermore, Fosgerau and Bierlaire (2009) show that the assumption of the Weibull distribution is associated with the discrete choice model having multiplicative error terms, and the log-transformation links the multiplicative model to the additive model for which the Gumbel distribution is…”