The Internet offers a number of advantages as a survey mode: low marginal cost per completed response, capabilities for providing respondents with large quantities of information, speed, and elimination of interviewer bias. Those seeking these advantages confront the problem of representativeness both in terms of coverage of the population and capabilities for drawing random samples. Two major strategies have been pursued commercially to develop the Internet as a survey mode. One strategy, used by Harris Interactive, involves assembling a large panel of willing respondents who can be sampled. Another strategy, used by Knowledge Networks, involves using random digit dialing (RDD) telephone methods to recruit households to a panel of Web-TV enabled respondents. Do these panels adequately deal with the problem of representativeness to be useful in political science research? The authors address this question with results from parallel surveys on global climate change and the Kyoto Protocol administered by telephone to a national probability sample and by Internet to samples of the Harris Interactive and Knowledge Networks panels. Knowledge and opinion questions generally show statistically significant but substantively modest difference across the modes. With inclusion of standard demographic controls, typical relational models of interest to political scientists produce similar estimates of parameters across modes. It thus appears that, with appropriate weighting, samples from these panels are sufficiently representative of the U.S. population to be reasonable alternatives in many applications to samples gathered through RDD telephone surveys.

Benefit-cost analysis remains the central paradigm used throughout the public sector. A necessary condition underlying efficient benefitcost analysis is an accurate estimate of the total value of the nonmarketed good or service in question. While economists have long measured the benefits of private goods routinely bought and sold in the marketplace, a much more difficult task faces the practitioner interested in estimating the total benefits of increased air and water quality, for example. In such cases, policy makers rely on stated preference methods (contingent markets) to provide signals of value. Recently there has been a lively debate about whether, and to what extent, "hypothetical bias" permeates benefit estimation in contingent markets.' This debate has proliferated among academics and practitioners over the past several decades, and continues to find its way into public disputes of damage assessment, development decisions, and discussions of optimal regulatory standards. This study extends the debate in a new direction by taking advantage of a unique opportunity we were provided at the University of Central Florida (UCF), where we were ap

No abstract

No abstract

While a number of validity tests exist for contingent valuation data, to date there are very few literature examples for contingent behavior (CB) data. The objective of this study is to test the validity of CB trip data for different levels of rock climbing access using data from surveys implemented before and after a policy restricting recreational access was imposed. Results from generalized Negative Binomial and seemingly unrelated Poisson regression models show significant sensitivity to scope, and suggest that CB data may be a valuable supplement to revealed preference data when policy proposals are outside the range of historical conditions. Copyright 2002, Oxford University Press.