An Objective Bayesian Analysis of the Change Point Problem Elías Moreno, George Casella and Antonio Garcia-Ferrer Universidad de Granada, University of Florida and Universidad Autónoma de Madrid August 3, 2004 Abstract The Bayesian literature on the change point problem deals with the inference of a change in the distribution of a set of time- ordered data based on a sample of fixed size. This is the so-called “retrospective or off-line” analysis of the change point problem. A related but different problem is that of the “sequential” change point detection, mainly analyzed from a frequentist viewpoint. While the former typically focuses on the estimation of the position in which the change point occurs, the latter is a testing problem which has a natural formulation as a Bayesian model selection problem. In this paper we provide such a Bayesian formulation, which generalizes previous formulations such as the well-known CUSUM stopping rule. We show that the conventional improper priors (also called non-informative, objective or default), cannot be used either for sequential detection of the change or for retrospective estimation. Then, we propose objective intrinsic prior distributions for the unknown model parameters. The normal and Poisson cases are studied in detail and examples with simulated and real data are provided. Keywords: change point, intrinsic priors, model selection, sequential detection, retrospective estimation. 1 Introduction There is an extensive literature on the subject of quick detection of changes in the parameters of a model of a stochastic system on the basis of sequential observations of the system, see for instance Lai (1995), and references therein. The simplest case of this problem can be described 1