Maximum likelihood and maximum product of spacings estimations for the parameters of skew-normal distribution under doubly type II censoring using genetic algorithm.

In this study, we use the maximum likelihood (ML) and the maximum product of spacings (MPS) methodologies to estimate the location, scale and skewness parameters of the skew-normal distribution under doubly type II censoring. However, it is known that these estimators cannot be obtained analytically because of nonlinear functions in the estimating equations. Therefore, numerical methods such as Nelder–Mead (NM), Newton–Raphson (NR), iteratively re-weighting algorithm (IRA), etc., are used to overcome this problem. In this study, different than the earlier studies, we use the genetic algorithm (GA) which is a population-based heuristic method based on the random search to find the estimates of the unknown parameters. In constructing the search space for GA, we utilize the robust confidence intervals to have a high convergence rate in GA. Then, we compare the efficiencies of the ML estimators obtained by using NM, NR, IRA, and GA methods and the efficiencies of the MPS estimators obtained by using NM and GA methods via an extensive Monte-Carlo simulation study. At the end of the study, we analyze the deep-groove ball bearings data to show the implementation of the proposed methodology. • ML and MPS estimates the parameters of Skew-normal under doubly type II censoring. • GA is used to obtain the estimates instead of traditional numeric algorithms. • Search space for GA is taken as data-driven confidence intervals of MML estimators. • GA obtains ML and MPS estimates of three parameters simultaneously and effectively • Simulation & Application results prove the superior performance of GA vs the others. [ABSTRACT FROM AUTHOR]

Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)