Bayesian and Non-Bayesian Analysis of the Log-Normal Distribution and Log-Normal Regression

Abstract In this article, Bayesian and non-Bayesian methods for estimating parameters of the log-normal distribution and of log-normal regression processes are considered. Posterior distributions for parameters of interest are derived and their properties are described. With respect to point estimation, a rather broad class of estimators is defined and, relative to this class, new minimal mean square error (MSE) estimators for the median and mean of the log-normal distribution and for the median and mean of the dependent variable in log-normal regressions are derived.