Bayesian quantile plots and statistical inference for nonlinear models in the two sample case with incomplete data
Martin T. Wells, Ram Chandra Tiwari · Communication in Statistics- Theory and Methods · 1989
Let F and G be continuous life distribution functions and be the horizontal distance from F to G at x. Assume that F and G are chosen according to independent Dirichlet processes with parameters α and β, respectively. Let and be the Bayes estimators of F and G based on the right censored data from F and G and the weighted squared error loss function. In this article the weak convergence of is studied. This extends the results of Doksum (1974) to the case of right censored data.