Bayesian Logistic Regression Model Choice via Laplace-Metropolis Algorithm

Following a bayesian statistical inference paradigm, weprovide an alternative methodology for analyzing a multivariate logisticregression. we use a multivariate normal prior in the bayesiananalysis. we present a unique bayes estimator associated with a priorwhich is admissible. the bayes estimators of the coefficients of themodel are obtained via mcmc methods. the proposed procedureis illustrated by analyzing a data set which has previously been analyzedby various authors. it is shown that our model is more preciseand computationally less taxing.