The Optimal Sample Size for Contingent Valuation Surveys: Applications to Project Analysis

One of the first questions that has to be answered in the survey design process is "How many subjects should be interviewed?" The answer can have significant implications for the cost of project preparation, since in Latin America and the Caribbean costs per interview can range from US$20 to US$100. Traditionally, the sample size question has been answered in an unsatisfactory way by either dividing an exogenously fixed survey budget by the cost per interview or by employing some variant of a standard statistical tolerance interval formula. The answer is not to be found in the environmental economics literature. But, it can be developed by adapting a Bayesian decision analysis approach from business statistics. The paper explains and illustrates, with a worked example, the rationale for and mechanics of a sequential Bayesian optimization technique, which is only applicable when there is some monetary payoff to alternative courses of action that can be linked to the sample data.