We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
A New Approach to Random Utility Modeling using the Dirichlet Multinomial Distribution.
- Authors
SHONKWILER, J. S.; HANLEY, NICK
- Abstract
In this paper we introduce a new econometric approach to analyzing recreational site choice data, the Dirichlet multinomial model. This model, which nests the standard conditional multinomial logit model, can accommodate over-dispersed data and may provide more efficient estimators of coefficients and consequent welfare measures than the standard conditional logit model, which is so widely used in the Random Utility Model approach to recreation demand. We illustrate this Dirichlet approach using a data set of rock climbers in Scotland, and study the impacts on per-trip consumers surplus of alternative management strategies for popular rock climbing sites. Results show that the Dirichlet multinomial approach produces coefficient and welfare estimates having smaller sampling variability in this case. We also compare classical welfare measures with their posterior equivalents, which allow for welfare changes to be dis-aggregated.
- Subjects
SCOTLAND; CONSUMER preferences; RECREATION industry; ROCK climbing; ECONOMIC statistics; ECONOMIC demand
- Publication
Environmental & Resource Economics, 2003, Vol 26, Issue 3, p401
- ISSN
0924-6460
- Publication type
Article
- DOI
10.1023/B:EARE.0000003597.88521.24