Percentile Estimators for Two-Component Mixture Distribution Models

The percentile estimators have a widespread usage in the estimation of distribution parameters because of simplicity and ease of computation. In this study, we investigate the percentile method for two-component mixture distribution models which are commonly used in modeling of heterogeneous univariate data sets. We have proposed percentile estimator for two-component mixture Weibull and two-component mixture Rayleigh distributions according to two different approaches. Performances of the defined percentile estimators were compared with maximum likelihood estimators using simulation. For this purpose, we used several criteria which are bias, mean squared error, mean absolute deviation, mean relative total error and running time of the algorithm. The benefits of the proposed methods have been illustrated by three different real data sets.