“…The Bayesian literature on the change point problem focuses on the retrospective analysis for situations where f 0 (x) and f 1 (x) belong to a parametric family of densities; see, for instance, Ferreira (1975), Smith (1975), Choy and Broemeling (1980), Smith and Cook (1980), Menzefrike (1981), Raftery and Akman (1986), Carlin et al(1992), among others. When f 0 (x) and f 1 (x) are densities belonging to a parametric family to be denoted as f(x|h 1 ) and f(x|h 2 ) respectively, where h 1 and h 2 are unknown points of a parameter space Q, the sampling density of the first n observations is…”