Venue: The Fuqua School of Business, Duke University, 1 Towerview Drive, Durham, NC 27708-0120
Presentation
Estimating WTP: Do Health Economists Accept Different Methodological Standards Than Environmental Economists?
BACKGROUND: New and better methods are constantly being developed in applied research. Eventually, state-of-the-art methods that are required for peer-reviewed publications become state-of-the-practice methods that are used in practical applications. Stated-preferences methods have been extensively used and tested for validity in environmental and health economics. However, the quality of data collected and the validity of statistical analysis are sensitive to a number of researcher decisions.
OBJECTIVES: The aim of this study is to quantify and compare the degree of the current consensus among active researchers in the rapidly evolving area of stated-preference methods in health and environmental valuation.
METHODS: Stated-preference (SP) methods include both contingent-valuation (CV) and conjoint-analysis (CA) or discrete-choice experiment approaches. Designing an SP study requires numerous judgments involving such considerations as what features of the good or service to include, which question format to use, how to develop and administer the survey, and how to estimate preference parameters to obtain valid, unbiased results. In CA applications, trade-off choice patterns reveal the underlying importance weights respondents use to evaluate alternatives. Employing the same method, we have developed a 'meta-survey' of this same type to elicit researchers' preferences for the methods themselves. We surveyed researchers who have published health and environmental valuation manuscripts in peer-reviewed journals on stated preference methods in the last 10 years. We asked these researchers to evaluate hypothetical studies, where one of the SP methods, either CV or CA, was used. The subjects compared a series of pairs of hypothetical studies with specified characteristics in either health or environmental applications. They were first asked which study they would recommend to use to inform policy decisions by a government agency, and then asked which study employs better methods.
RESULTS: We received 91 completed health and 136 environmental surveys. We used mixed-logit and ranked-logit models to estimate researchers' preferences. Researchers were more likely to recommend a study to inform policy decisions if the study is in a double-bounded CV or discrete-choice CA format; if the survey is pre-tested or passed a scope test. Researchers did not think that statistical analysis that involved advanced modeling is better than basic modeling for policy studies. However, researchers who have more experience with CA studies thought advanced modeling is better. The biggest difference between the two types of researchers involved the experimental-design attribute. While environmental researchers had clear preferences on experimental designs, the type of experimental design did not matter for the policy recommendation for health researchers.
CONCLUSION: Using an SP method to evaluate SP methods was a convenient and valid way of investigating current researcher preferences. Our study results indicate that researchers may have similar preferences on some of the study features. The experience of researcher, especially the familiarity with the methods may affect their preferences.