Abstract. Full text article available at https://doi.org/10.1515/eqc-2017-0009
We consider the Dagum distribution for estimating the reliability of a k-component stress-strength system with different shape values of the shape parameter. We assume that the system has strength modelled by k independent and identically distributed random variables, and each system’s component experiences random stress. We construct maximum likelihood estimators for the system’s reliability and study their asymptotic properties. We evaluate the small sample performance of the estimators through Monte Carlo simulation. Finally, we illustrate the procedure using real data.