Statistical Inference for Kumaraswamy Distribution Based on Generalized Order Statistics with Applications

In this paper, non-Bayesian and Bayesian approaches are used to obtain point and interval estimation of the shape parameters, the reliability and the hazard rate functions of the Kumaraswamy distribution. The estimators are obtained based on generalized order statistics. The symmetric and asymmetric loss functions are considered for Bayesian estimation. Also, maximum likelihood and Bayesian prediction for a new observation are found. The results have been specialized to Type II censored data and the upper record values. Comparisons are made between Bayesian and non-Bayesian estimates via Monte Carlo simulation. Moreover, the results are applied on real hydrological data.