A study of shifting models in life tests via bayesian approach using semi-or-used priors (SOUPS)

Abstract

SummaryThis paper analyses the shift in parameter of a life test model. This analysis depends on the prediction of order statistics in future samples based on order statistics in a series of earlier samples in life tests having a general exponential model. While a series of k samples are being drawn, model itself undergoes a change. Firstly, a single shift is considered and the effect of this shift on the variance is discussed. Generalisation with s shifts (s~k) in k samples is also taken up and the semi-or-used priors (SOUPS) have been used to get predictive distributions. Finally, shift after i (i~_k) stages, from exponential to gamma model is considered and for this case effect of the shift on the variance as well as on the Bayesian prediction region (BPR) is analysed along with set of tables.