Estimating recreation demand with on-site panel data: An application of a latent class truncated and endogenously stratified count data model.

In this paper, we present an extension of Shaw’s (1988) and Englin and Shonkwiler’s (1995) count data travel cost models corrected for on-site sampling to a panel data setting. We develop a panel data negative binomial count data model that corrects for endogenous stratification and truncation. We also incorporate a latent class structure into our panel specification which assumes that the observations are drawn from a finite number of segments, where the distributions differ in the intercept and the coefficients of the explanatory variables. Results of this model are compared to some of the more common modelling approached in the literature. The chosen models are applied to revealed and contingent travel data obtained from a survey of visitors to a beach on the outskirts of Galway city in Ireland. The paper argues that count data panel models corrected for on-site sampling may still be inadequate and potentially misleading if the population of interest is heterogeneous with respect to the impact of the chosen explanatory variables.