Unit-Weibull Distribution: Different Method of Estimations

Authors : Hasan Hüseyin GÜL

Pages : 547-560

Doi:10.31466/kfbd.1239446

View : 34 | Download : 39

Publication Date : 2023-06-15

Article Type : Research Paper

Abstract :Recently, the unit-Weibull insert ignore into journalissuearticles values(UW); distribution is used quite effectively in analyzing lifetime data. The main goal of this article is to investigate the performance of seven estimation methods, namely maximum likelihood insert ignore into journalissuearticles values(ML);, least square insert ignore into journalissuearticles values(LS);, weighted least square insert ignore into journalissuearticles values(WLS);, Anderson-Darling insert ignore into journalissuearticles values(AD);, right-tail Anderson-Darling insert ignore into journalissuearticles values(RAD);, Cramer-von-Mises insert ignore into journalissuearticles values(CVM); and percentile insert ignore into journalissuearticles values(PCE); for parameter estimation. An extensive Monte Carlo simulation study is considered to compare the performances of these methods through biases and mean square errors insert ignore into journalissuearticles values(MSEs);. The numerical results show that the PCE estimator has significantly smaller MSE value for different sample sizes and parameter values in most cases. In addition, the ML and LS estimators have lower bias values than the other estimators in general. Finally, a real data set is presented for illustrative purposes.
Keywords : Unit Weibull dağılımı, En çok olabilirlik, Anderson Darling, En küçük kareler