Prediction of future generalized order statistics based on two-parameter exponential distribution for large samples

Abstract

ABSTRACT Exact and asymptotic distributional properties are discussed in detail for two mean-squared error consistent point predictors of future-generalized order statistics (GOSs) based on two-parameter exponential distribution. These predictors work even if some observed data were missing. For each point predictor, the asymptotic distribution of the normalized difference between the future GOS and its point predictor is derived, when the scale parameter is known or unknown. It is revealed that the asymptotic distributions of these normalized differences are equal when the scale parameter is known. Two asymptotic prediction intervals of the future GOS are constructed whenever the scale parameter is known or unknown. Furthermore, two tests of outliers are proposed relying on the point predictors. Finally, a simulation study is conducted and a real data set is analyzed for illustrative purposes.