Estimation methods for the three-parameter gamma distribution

İçli, Tülay
As a positively skewed distribution, gamma distribution plays an important role in the analysis of sample data originating from life-span, reaction time, reliability, | survival and related studies. Therefore, it is worth-while to deal with the estimation of its parameters. Since gamma distribution does not satisfy some of the regularity conditions, it is a member of non-regular distributions. Inclusion of the threshold parameter creates complications. This parameter can be estimated by the first order statistic, since it contains more information about the threshold parameter than the others do. However, it has been shown that this estimator does not yield the desirable statistical properties. Thus, the introduction of new estimators (approximations or modifications) is needed. In the present study, a literature survey is done to deal with the difficulties of existing estimation techniques for the three-parameter gamma distribution, and a Comparative study is performed for different simulated gamma populations to find the best estimation technique under consideration. It is obtained that corrected likelihood method is relatively better than the others for estimating the three parameters in terms of their biases and mean squared errors.
Citation Formats
T. İçli, “Estimation methods for the three-parameter gamma distribution,” Middle East Technical University, 1991.