PARAMETER ESTIMATION BASED ON MAXIMUM LIKELIHOOD ESTIMATION METHOD FOR WEIBULL DISTRIBUTION USING DRAGONFLY ALGORITHM

Authors : Aynur YONAR, Nimet YAPICI PEHLİVAN

Pages : 84-90

Doi:10.22531/muglajsci.973403

View : 16 | Download : 10

Publication Date : 2021-12-31

Article Type : Research Paper

Abstract :Three-parameter insert ignore into journalissuearticles values(3-p); Weibull distribution is commonly used in sciences such as engineering, reliability, and renewable energy. Thus, a great number of studies have been conducted on the estimation for the parameters of this distribution. One of the mostly utilized methods for estimating the unknown parameters of the Weibull distribution in the related literature is Maximum likelihood insert ignore into journalissuearticles values(ML); method. In this study, a population-based novel heuristic method is proposed to use the Dragonfly Algorithm insert ignore into journalissuearticles values(DA); for obtaining the Maximum Likelihood estimates of three-parameter Weibull distribution. Inspired by the static and dynamic swarming behavior of the dragonflies in nature, Dragonfly algorithm has been introduced. These behaviors ensure that the algorithm has a high exploration and exploitation. An extensive Monte-Carlo simulation study is conducted to show the performance of the DA. Furthermore, the performance of DA is compared with other algorithms well known in the literature. Finally, a real data set is analyzed to show the applicability of the ML estimation based on the DA.
Keywords : Dragonfly Algorithm, Maximum Likelihood Estimation, Monte Carlo Simulation, Weibull Distribution