A new procedure : bayesian selection to find the best of geometric population under general loss function

Abstract EN

In many practical situations the experimenter is confronted with the problem of choosing the best one of a number of populations or categories or ranking them according to their performance.

This paper derives a procedure for selecting the better of Two Geometric populations employing a decision-theoretic Bayesian framework with Beta prior under general loss function.

The numerical results for this procedure are given by using Math Works Matlab ver 7.0.1 with different loss functions constant, linear and quadratic, where in one equation we can obtain the Bayes risk for the three types of the loss functions : constant, linear and quadratic.