Statistical Inference under Copula Approach of Accelerated Dependent Generalized Inverted Exponential Failure Time with Progressive Hybrid Censoring Scheme

The problem of statistical inference in reliability theory for the competing risks model under accelerated life testing (ALT) have a great significance. In practice, independent variables are assumed for convenience, which do not agree with the nature of the problem at hand. In this paper, we consider the constant stress accelerated life testing (CS-ALT) of dependent competing risks model for generalized inverted exponential distribution (GIED). The dependence structure is described by the copula approach between variable. Under consideration that units is failing by only two dependent causes of failure under constant stress ALTs and type-I progressive hybrid censoring scheme (PHCS), the model parameters are estimated with maximum likelihood method by using the bivariate Pareto copula function. The asymptotic confidence intervals with approximate Bootstrap confidence intervals are constructed. Under consideration two stress levels the set of real data are analyzed for illustrative purposes. For different measures of Kendall’s tau and censoring schemes Monto Carlo simulation study is constructed