Distinguishing taste variation from error structure in discrete choice data

Citation
J. Swait et A. Bernardino, Distinguishing taste variation from error structure in discrete choice data, TRANSP R B, 34(1), 2000, pp. 1-15
Citations number
35
Categorie Soggetti
Politucal Science & public Administration","Civil Engineering
Journal title
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
ISSN journal
01912615 → ACNP
Volume
34
Issue
1
Year of publication
2000
Pages
1 - 15
Database
ISI
SICI code
0191-2615(200001)34:1<1:DTVFES>2.0.ZU;2-W
Abstract
We propose as a practice that researchers investigate other sources of hete rogeneity besides taste variation in the search for parsimonious recommenda tions about new product development and marketing program design. Some evid ence exists that regularities in choice processes may be more common than p reviously thought (Louviere and Swait, 1996, Louviere et al., 1999; see als o Stigler and Becker, 1977). In fact, it may be that taste homogeneity is m ore prevalent than expected, if we recognize other sources of heterogeneity properly. In this paper we show how discrete choice models confound taste heterogeneity and differences in error structure. We then illustrate the us e of the Tree Extreme Value (TEV) model to investigate taste homogeneity in three trans-oceanic air travel markets, while controlling for error struct ure heterogeneity, We conclude that partial taste homogeneity exists across the markets, despite accentuated cultural differences; in addition: two of the routes exhibit a much higher degree of taste homogeneity, despite a si gnificant difference in trip length. (C) 1999 Elsevier Science Ltd. All rig hts reserved.