Modeling Site Specific Heterogeneity in an On-Site Stratified Random Sample of Recreational Demand

Using estimation of demand for the George Washington/Jefferson NationalForest as a case study, it is shown that in a stratified/clustered on-sitesample, latent heterogeneity needs to be accounted for twice: first to accountfor dispersion in the data caused by unobservability of the process that resultsin low and high frequency visitors in the population, and second tocapture unobservable heterogeneity among individuals surveyed at differentsites according to a stratified random sample (site specific effects). It is shownthat both of the parameters capturing latent heterogeneity are statistically significant.It is therefore claimed in this paper, that the model accounting forsite-specific effects is superior to the model without such effects. Goodnessof fit statistics show that our empirical model is superior to models that donot account for latent heterogeneity for the second time. The price coefficientfor the travel cost variable changes across model resulting in differences inconsumer surplus measures. The expected mean also changes across differentmodels. This information is of importance to the USDA Forest Servicefor the purpose of consumer surplus calculations and projections for budgetallocation and resource utilization.