"protested" in some way the hypothetical market. The Water Resources Council recommends 

 asking a follow-up question to determine the reasons for "no" responses and decide which ones 

 were protest bids. The upland game bird survey used the same format for this question as 

 earlier surveys, which was: 



"If no, would you have made the trip if your share of the expenses had been only $1 .00 

 more?" Following a "no" to this question, the respondent was asked: "If no, could you 

 briefly explain why not?" 



Valid reasons for saying no included a) could not afford higher trip costs, b) hunter said he 

 would hunt elsewhere if costs increased, c) trip just wouldn't be worth the higher costs. Protest 

 responses included a) hunter saying he/she did not understand the question or b) indicated they 

 opposed increased fees or taxes. 



A total of twenty eight responses were excluded from the data set due to being protest bids or 

 outliers. 



Model Specification 



The estimates of net economic value for an upland game bird hunting trip were determined from 

 the sampled hunters' responses to the contingent valuation questions. The responses were 

 analyzed using a logistic regression model. Duffield and Patterson (1991) provide a 

 comprehensive discussion of the theory and techniques concerning these models. 



Economic theory suggests that certain variables will influence a hunters response. A bivariate 

 logit model was used in this study that regressed "yes" and "no" responses against bid amount. 

 It is expected that as the bid amount increases, the probability of a "yes" response will drop. 

 The following bivariate model was used in this study: 



In (P/l-P) = BO - Bl In(Bid) 



where: P = probability of a "yes" response 



Bid = increased trip costs respondent was asked to pay 



The estimated equations are shown in Appendix B. The coefficients for the independent variable 

 In(Bid) had the expected sign (negative) and were significant at the .05 level. These results 

 show the responses are consistent with economic theory and the model used generally provided 

 a good fit to the data. 



16 



