A BAYESIAN-APPROACH FOR ESTIMATING TARGET MARKET POTENTIAL WITH LIMITED GEODEMOGRAPHIC INFORMATION

The authors develop a Bayesian approach for inferring the joint distri bution of several demographic variables when only information about th e marginal distribution of each variable is known and when there is pr ior information about the correlation between the variables, Using pub lic domain U.S. Census Bureau geodemographic data for Sioux Falls and the state of South Dakota, they apply the approach to four specific ma rketing problems, two involving direct mail advertising campaigns and two involving the location of a retail site. The empirical application s illustrate the serious bias that results from the assumption that th e demographic variables are independent of each other, Overall, the Ba yesian approach recovers the underlying joint distribution of the vari ables of interest well and is unique in its ability to provide a measu re of uncertainty about the resulting estimates, Hypothesis testing an d the construction of confidence intervals are illustrated in the cont ext of a retail site location application. The results of a Monte Cart e experiment indicate that the Bayesian approach recovers joint densit ies under a variety of conditions in a robust manner.