COMPUTATION OF POSTERIOR MODE FOR LOCATION PARAMETER AND CONDITIONAL EXPECTATION FOR SCALE PARAMETER OF NORMAL SEQUENCE

摘要

We introduce a novel Double Exponential and Half- Normal distributions as a sparsity promoting priors, respectively, for the location and scale parameters assuming independent, of normal sequence that allows to specification of constraints which describes the prior distribution as heavy tailed nature. We conceive an ideology rather than new and different, to overcome the difficulty of numerical integration of location parameter over infinite range, developed an algorithmic procedure through which posterior mode and mean obtained as Bayes estimates of location parameter. Bayes estimates of scale parameter conditional on the estimates of location parameter is also obtained. To illustrate the methodology of the novel procedure, simulation study carried out and show that their better performance through computing the Bayesian estimates and MSE of the Bayes estimates of posterior mode, mean and variance.