Comparisons of six different estimation methods for log-Kumaraswamy distribution

Abstract

In this paper, it is considered the problem of estimation of unknown parameters of log-Kumaraswamy distribution via Monte-Carlo simulations. Firstly, it is described six different estimation methods such as maximum likelihood, approximate bayesian, least-squares, weighted least-squares, percentile, and Cramer-von-Mises. Then, it is performed a Monte-Carlo simulation study to evaluate the performances of these methods according to the biases and mean-squared errors of the estimators. Furthermore, two real data applications based on carbon fibers and the gauge lengths are presented to compare the fits of log-Kumaraswamy and other fitted statistical distributions.

Estimating the Parameters of Xgamma Weibull Distribution

“…The acceptance-rejection algorithm is used to generate the data from distribution. BFGS algorithm is carried out to get the five estimates given in ( 5)- (9). The simulation results are summarized via Figs.…”

“…The authors also discussed some properties and different estimation methods such as maximum likelihood, ordinary and weighted least squares, percentile and maximum product spacing this new distribution in [8]. The methods of estimation for log-Kumaraswamy distribution were studied in [9]. Afify et al [10] considered different methods of estimation for Weibull Marshall-Olkin Lindley distribution.…”