Comparison of two methods maximum likelihood and Weighted Least Square method to estimate of Survival function (exponential - second order gamma) Mixed distribution


This paper presented the idea of estimating the survival function of the mixed probability model (exponential - gamma of the second order) (EG), using the Maximum Likelihood method and the Weighted Least Square method, in order to obtain the best method for estimating the function above from Through the comparison between the two methods of estimation referred to and thus by employing the experimental data (Simulation) that are generated using the method of rejection and acceptance, and for several sizes of samples (30,60,100), the outputs of the experimental tables showed the preference of the weighted least squares method in estimating the survival function in the estimate over the method Maximum Likelihood, for all default values and for all sample sizes, by using the well-known statistical scale (Mse) average mean squares of error.