Reversible jump Markov chain Monte Carlo computation and Bayesian model determination

@article{green1995, abstract = {Markov chain Monte Carlo methods for Bayesian computation have until recently been restricted to problems where the joint distribution of all variables has a density with respect to some fixed standard underlying measure. They have therefore not been available for application to Bayesian model determination, where the dimensionality of the parameter vector is typically not fixed. This paper proposes a new framework for the construction of reversible Markov chain samplers that jump between parameter subspaces of differing dimensionality, which is flexible and entirely constructive. It should therefore have wide applicability in model determination problems. The methodology is illustrated with applications to multiple change-point analysis in one and two dimensions, and to a Bayesian comparison of binomial experiments. 10.1093/biomet/82.4.711}, author = {Green, Peter J. }, citeulike-article-id = {2529750}, doi = {http://dx.doi.org/10.1093/biomet/82.4.711}, journal = {Biometrika}, keywords = {case2}, month = {December}, number = {4}, pages = {711--732}, posted-at = {2008-03-13 23:00:10}, priority = {2}, title = {Reversible jump Markov chain Monte Carlo computation and Bayesian model determination}, url = {http://dx.doi.org/10.1093/biomet/82.4.711}, volume = {82}, year = {1995} }

TY - JOUR ID - green1995 L3 - citeulike-article-id:2529750 TI - Reversible jump Markov chain Monte Carlo computation and Bayesian model determination JF - Biometrika VL - 82 IS - 4 SP - 711 EP - 732 N2 - Markov chain Monte Carlo methods for Bayesian computation have until recently been restricted to problems where the joint distribution of all variables has a density with respect to some fixed standard underlying measure. They have therefore not been available for application to Bayesian model determination, where the dimensionality of the parameter vector is typically not fixed. This paper proposes a new framework for the construction of reversible Markov chain samplers that jump between parameter subspaces of differing dimensionality, which is flexible and entirely constructive. It should therefore have wide applicability in model determination problems. The methodology is illustrated with applications to multiple change-point analysis in one and two dimensions, and to a Bayesian comparison of binomial experiments. 10.1093/biomet/82.4.711 KW - case2 AU - Green, Peter PY - 1995/12/01/ UR - http://dx.doi.org/10.1093/biomet/82.4.711 ER -