New qualitative choice models incorporating individual and choice characteristics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

New qualitative choice models incorporating individual and choice characteristics

Abstract

In the econometric framework, multinomial and conditional logit models are the most usual regression models for qualitative choices. They differ by their parametrization while sharing the canonical link function. This link function can be decomposed into the reference ratio of probabilities and the logistic cumulative distribution function (cdf). We propose to conserve the reference ratio, appropriate for qualitative choices, but to select the cdf among an enlarged family containing the Student cdf for instance. These new qualitative choice models often outperform logit models in terms of likelihood and error rate of classification and stay easily interpretable. This is illustrated with a benchmark dataset of travel demand between Sydney and Melbourn.
Fichier principal
Vignette du fichier
Peyhardi2015.pdf (385.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01242841 , version 1 (14-12-2015)

Identifiers

  • HAL Id : hal-01242841 , version 1

Cite

Jean Peyhardi. New qualitative choice models incorporating individual and choice characteristics. 30th International Workshop on Statistical Modelling (IWSM 2015), Statistical Modelling Society, Jul 2015, Linz, Austria. pp.319-323. ⟨hal-01242841⟩
378 View
45 Download

Share

Gmail Facebook X LinkedIn More