Interval estimation for failure data from a load-sharing system

In a load-sharing system, total workload is shared by all components and failure of one component increases workload of the surviving ones. The time interval between two consecutive component failures reflects component reliability under different workloads and is of interest to us. This study develops some methods to derive both exact and approximate confidence intervals for parameters in load-sharing systems. We also propose a method to test exponential distribution assumption in our model. Two examples representing different types of real problems are used to demonstrate the performance of our methods.