Bayesian and non-Bayesian prediction for progressively type-ii censored competing risks data from Kumaraswamy model

Bayesian prediction for progressive type-II censored data with a competing risk model is obtained for the Kumaraswamy distribution using the Tierney and Kadane approximation form. In this paper, Bayesian and non-Bayesian prediction problems are considered for progressive type-II censored data, under the competing risk Kumaraswamy distribution. For the three-parameter Kumaraswamy model, the mathematical analysis is theoretically more complicated and more difficult. Therefore, the approximate form of Tierney and Kadane [Accurate approximations for posterior moments and marginal densities. J Am Stat Assoc. 1986;81(393):82–86.] is used to simplify the Bayes predictive density function of future data. Finally, a Monte Carlo simulation study and real-life data are used to demonstrate the applicability of the suggested methodology.