Narrow choice sets in a random utility model of recreation demand.

摘要

A sub-sample of 3519 fishing license holders who had visited 814 lakes in Maine, USA, were interviewed to determine the applicability of the random utility model of recreation demand. It is hypothesized that careful formulation of the choice set focusing on the sites of policy interest and their closest substitutes will give reasonably accurate welfare estimates. Nearby sites were used as close substitutes and treat more distant sites as aggregate alternatives in our application to fishing in Maine. It is found that the welfare estimates are rather sensitive to narrowing choice sets in this manner. The sensitivity largely tracts variation in the estimated travel cost coefficient across the different models considered.