Dynamic invariant multinomial probit model: Identification, pretesting and estimation

Roman Liesenfeld , Jean-François Richard

We present a new specification for the multinomial multiperiod Probit model with autocorrelated errors. In sharp contrast with commonly used specifications, ours is invariant with respect to the choice of a baseline alternative for utility differencing. It also nests these standard models as special cases, allowing for data based selection of the baseline alternatives for the latter. Likelihood evaluation is achieved under an Efficient Importance Sampling (EIS) version of the standard GHK algorithm. Several simulation experiments highlight identification, estimation and pretesting within the new class of multinomial multiperiod Probit models.

Mots clés: C35; C15; Discrete choice; Efficient Importance sampling; Invariance; Monte-Carlo integration; Panel data; Simulated maximum likelihood

Roman Liesenfeld, Jean-François Richard. Dynamic invariant multinomial probit model: Identification, pretesting and estimation. Econometrics, 2009, 155 (2), pp.117. ⟨10.1016/j.jeconom.2009.09.021⟩. ⟨hal-00628315⟩