Truncation and endogenous stratification in various count data models for recreation demand analysis

This paper extends the truncated and endogenously stratified Poisson and negative binomial models to three alternative discrete distributions, namely the generalized Poisson, geometric, and Borel distributions. Our primary intention here is to demonstrate how improper treatment of the data generates divergent outcomes by applying those distributions to recreation trip data gathered from surveys of visitors to an indigenous horse park in Japan. Our empirical application shows that failure to account for overdispersion, truncation, and endogenous stratification leads to substantial changes in parameter estimates and their standard errors. The parameter on the travel cost tends to be underestimated in absolute value in the standard setups. This results in serious overestimation of the economic benefit that the recreation site offers to society. Even when the endogenous stratification is incorporated, ignoring overdispersion causes the per capita per trip consumer's surplus to be over seven times larger than that obtained when endogenous stratification and overdispersion are considered. -- Count data models ; Endogenous stratification ; Overdispersion ; Recreation demand analysis ; Consumer's surplus