Bayesian Estimation and Prediction for Pareto Data

Abstract Data from a classical Pareto distribution are to be used to make inferences about the inequality and precision parameters. In addition, it is desired to predict the behavior of further observations from the distribution. Three typical data configurations are considered (iid and two types of censoring). Dependent conjugate prior analyses are reviewed and are compared with an analysis involving independent priors for the inequality and precision parameters. It is argued that mathematical tractability should be, perhaps, a minor consideration in the choice of priors. A comparative example is included.