A Review of Logit Models with Implications for Modeling Recreation Choices

Abstract

The use of logit models to predict recreation activity and site choice is increasing. This paper summarizes the properties of binomial and multinomial logit models, reviews applications of these models in recreation, and provides guidance to the technical literature on estimation techniques. The independence from irrelevant alternatives (IIA) property of the multinomial logit model is discussed and recommendations are made for improving models of recreation choice.