2002 World Congress of Environmental and Resource Economists

This paper develops simulation-based strategies for introducing general correlation patterns into the error structures of demand system models of recreation demand. Although demand system modeling of recreation choices has evolved rapidly in recent years, introducing general correlation patterns has remained elusive except for the recent paper of Shonkwiler [1999]. For illustration, the strategies proposed in this paper are applied to data from the 1997 Iowa Wetlands Survey. Correlated and independent versions of a continuous additively separable Kuhn-Tucker demand system model as well as a zero-inflated Poisson count data demand system model are estimated and compared. Welfare estimates for a twenty percent increase in pheasant counts in the Prairie Pothole Region and a $50 access fee for the Eastern and Western Riverine Wetlands suggest that introducing correlations into the error structures has a small marginal effect on the policy inference drawn from models.



	Paper Title:	What Are The Welfare Implications Of Introducing General Correlation Patterns Into Demand System Models?
	Presenting Author:	Roger H Von Haefen (Bureau of Labor Statistics)
	Coauthor 1:
	Coauthor 2:
	Coauthor 3:
	Abstract:	This paper develops simulation-based strategies for introducing general correlation patterns into the error structures of demand system models of recreation demand. Although demand system modeling of recreation choices has evolved rapidly in recent years, introducing general correlation patterns has remained elusive except for the recent paper of Shonkwiler [1999]. For illustration, the strategies proposed in this paper are applied to data from the 1997 Iowa Wetlands Survey. Correlated and independent versions of a continuous additively separable Kuhn-Tucker demand system model as well as a zero-inflated Poisson count data demand system model are estimated and compared. Welfare estimates for a twenty percent increase in pheasant counts in the Prairie Pothole Region and a $50 access fee for the Eastern and Western Riverine Wetlands suggest that introducing correlations into the error structures has a small marginal effect on the policy inference drawn from models.
	Link to paper:	Not available

	Session / Day / Time	2E / Monday / 10:15 - 11:45 am

	Please use your browser's "back" button to get to the previous page.