On Estimation in Exponential Power Distribution and its Applications

This paper addresses various properties of the exponential power distribution such asraw and conditional moments, mean residual life, mean past lifetime, quantile function and order statistics. Maximum likelihood and Bayesian estimation methods are used to estimate the scale and shape parameters as well as survival characteristics of the distribution. We obtain maximum likelihood and Bayes estimates of the parameters along with their standard errors and confidence intervals using Monte Carlo simulation and Markov Chain Monte Carlo (MCMC) techniques taking various sample sizes. For Bayesian estimation, independent gamma priors are used. The applicationof the model is illustrated by taking a real dataset using three methods viz .goodness-of-fit criteria, goodness-of-fit statistics and classical goodness-of-fit plots .