We study the problem of finding an optimal assortment products maximizing expected revenue, in which customer preferences are modeled using a nested logit choice model. This is known to be polynomially solvable specific case and NP-hard otherwise, with only approximation algorithms existing literature. provide exact general method that embeds tailored Branch-and-Bound algorithm into fractional ...

In contrast to the classical discrete choice experiment, the respondent in a rank-order discrete choice experiment, is asked to rank a number of alternatives instead of the preferred one. In this paper, we study the information matrix of a rank order nested multinomial logit model (RO.NMNL) and introduce local D-optimality criterion, then we obtain Locally D-optimal design for RO.NMNL models in...

Substantive income effects are incorporated in a logit or nested-logit model by assuming that utility is a piece-wise linear spline function of residual income. Specific income data are not required, only income by category. Expected compensating variation is easily and accurately approximated by the difference between expected maximum utility in the proposed and initial state, multiplied by th...

The A.C. Nielson household scanner panel is used to analyze factors affecting brand-size choices for spaghetti. These data link product purchases, which are scanned, with household demographics and market information on the store where purchased. A multinominal logit model and a nested logit model are specified and estimated. In addition to the effects of inventory and brand loyalty, the most i...

We discuss some empirical and methodological issues arising when the Cox test statistic for non-nested models is used to test the probit vs. logit specifications. As an example, we consider the models in Bardasi and Monfardini (1997) for the occupational choice by Italian workers among the private, public and self-employed options. Different versions of the test are compared. The bootstrap tech...

The application of compositional data analysis through log ratio transformations corresponds to a multinomial logit model for the shares themselves. This model is characterized by the property of Independence of Irrelevant Alternatives (IIA). IIA states that the odds ratio –in this case the ratio of shares – is invariant to the addition or deletion of outcomes to the problem. It is exactly this...

We show that the distributions of random coefficients in various discrete choice models are nonparametrically identified. Our identification results apply to static discrete choice models including binary logit, multinomial logit, nested logit, and probit models as well as to dynamic programming discrete choice models. In these models the only key condition we need to verify for identification ...

This thesis examines how to model the choice of individual travelers among various possible travel alternatives in the airline industry. A review of the models used to represent that choice situation in the Passenger OriginDestination Simulator (PODS) was undertaken for two reasons. First, the development of computational capabilities has lead to advancements in consumer choice theory that enab...