A comparison of likelihood and Bayesian inference for the threshold parameter in the inverse Gaussian distribution

Abstract

Likelihood and Bayesian inferences for the threshold parameter of the three parameter inverse Gaussian distribution are compared and contrasted. When there is no prior information available and sample size is moderate, theoretical and empirical results suggest advantages to the Bayesian approach. Use of the conjugate prior can favorably affect the Bayesian inference in a substantial way. Copyright © 1998 by Marcel Dekker, Inc.