摘要：The implicit price (hedonic) equation for the housing market in a coastal town in southern Rhode Island was estimated using a conditional Box-Cox maximum likelihood procedure. Linear, log-linear, and semi-log functional forms were rejected with 95% confidence. Estimates of marginal implicit prices for water related attributes (view of, frontage on, and proximity to a coastal salt water pond) derived from these rejected models were quite different from those determined from the optimal functional form. This result has important ramifications for public policy, as is shown in an example, since these attributes were found to be highly valued in the housing market.
