BAYESIAN ESTIMATION OF ERLANG DISTRIBUTION UNDER DIFFERENT PRIOR DISTRIBUTIONS

This paper addresses the problem of Bayesian estimation of the parameters of Erlangdistribution under squared error loss function by assuming different independent informativepriors as well as joint priors for both shape and scale parameters. The motivation is to explore themost appropriate prior for Erlang distribution among different priors. A comparison of the Bayesestimates and their risks for different choices of the values of the hyperparameters is alsopresented. Finally, we illustrate the results using a simulation study as well as by doing real dataanalysis.