The logistic distribution is widely used in biostatistics and economics. In this paper, we provide some suitable pivotal quantities for constructing prediction intervals for the jth future-ordered observation from the two-parameter logistic distribution based on censored samples. Our method is more general in the sense that it can be applied to any data scheme. We present a simulation of our method to analyze its performance. Two illustrative examples are also included. For further study, our method is easily applied to other location and scale family distributions.
Journal of Statistical Computation and Simulation 77(5) ： p.389-405