On the Relationship Between Markov chain Monte Carlo Methods for Model Uncertainty

By Simon J. Godsill. 2001

296 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d30d25720e7f739687de1191d13c21ab986d6a5e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Model choice using reversible jump Markov chain Monte Carlo (2012, methodology): “Godsill’s (2001) formulation extends Equation (7) to allow the parameter vectors k to overlap arbitrarily, and embraces both product space and reversible jump methods, facilitating comparisons between them.”
Handbook of Markov Chain Monte Carlo: Hardcover: 619 pages Publisher: Chapman and Hall/CRC Press (first edition, May 2011) Language: English ISBN-10: 1420079417 (2012, background): “) Green (2003), Godsill (2003), and Hastie (2004) discuss a number of modifications to this general framework, including improving efficiency and relaxing the requirement of unimodal densities π(k, θk | x) to realize high between-model acceptance rates. Naturally, the required knowledge of first- an”
Spatial dynamic factor analysis (2008, methodology): “The above RJMCMC algorithm can be thought of as a particular case of the Metropolised Carlin and Chib method (Godsill 2001, and Dellaportas, Forster, and Ntzoufras 2002), where the proposal distributions generating both new model dimension and new parameters depend on the current state of the chain…”
BAYESIAN MODEL ASSESSMENT IN FACTOR ANALYSIS (2004, background): “Additional useful references in this general area include, for example, Gilks, Richardson and Spiegelhalter (1996), DiCiccio, Kass, Raftery and Wasserman (1997) and Godsill (2001), which study comparisons and connections between some of the various methods just referenced.”
Estimating the Integrated Likelihood via Posterior Simulation Using the Harmonic Mean Identity (2006, methodology): “A general approach to estimating posterior model probabilities is to use transdimensional MCMC, pioneered by Green (1995) with his introduction of reversible jump MCMC; a review of this area is given by Sisson (2005). These methods can be used to estimate Bayes factors, but not the underlying integr”
Efficient construction of reversible jump Markov chain Monte Carlo proposal distributions (2003, methodology): “An approach to transmodel dynamics, in which the algorithm stores a vector for each model at every iteration, has been introduced by Carlin and Chib (1995) and recently extended to a general framework, which also includes the reversible jump algorithm as described above, by Godsill (2001).”
Marginal likelihood estimation via power posteriors (2008, methodology): “Other across-model search strategies include those of Godsill (2001) and Carlin and Chib (1995).”
The NANOGrav 12.5 yr Data Set: Search for an Isotropic Stochastic Gravitational-wave Background (2020, methodology): “For disjoint models, models that are not easily distinguished parametrically, and indeed all model selection in this paper, we used the product-space method (Carlin & Chib 1995; Godsill 2001; Hee et al. 2015).”
The NANOGrav 15 yr Data Set: Evidence for a Gravitational-wave Background (2023, methodology): “When comparing disjoint models with different likelihoods (e.g., hd versus curn), we use product-space sampling (Carlin & Chib 1995; Godsill 2001).”
Bayesian Changepoint Analysis for Extreme Events (Typhoons, Heavy Rainfall, and Heat Waves): An RJMCMC Approach (2010, methodology): “To overcome this problem, Green (1995) first introduced the reversible jump Markov chain Monte Carlo (RJMCMC) algorithm as a simultaneous integrative approach to deal with the model selection problem.”
Reversible Jump Markov Chain Monte Carlo Strategies for Bayesian Model Selection in Autoregressive Processes (2004, background): “Moreover, Godsill (2001) and Troughton and Godsill (1997) do not consider the case where the initial state is unknown and random.”
Extension of the bayesian alphabet for genomic selection (2011, background): “4 in Godsill (2001) [15].”
A guide to Bayesian model selection for ecologists (2015, background): “In the big picture, Godsill (2001) and O’Hara and Sillanpaa (2009) show that the RJMCMC and indicator variable selection approaches are related.”
Bayesian inference of chemical kinetic models from proposed reactions (2015, background): “On the other hand, across-model sampling offers a solution in cases where the number of models is large (Carlin and Chib, 1995; Dellaportas et al., 2002; Godsill, 2001; Green, 1995).”
The NANOGrav 11 Year Data Set: Pulsar-timing Constraints on the Stochastic Gravitational-wave Background (2018, methodology): “For disjoint models (in our case, a model consisting of a Hellings–Downs-correlated red process plus pulsar noise, vs. a model consisting of a common-amplitude, spatiallyuncorrelated red process plus pulsar noise) we use a productspace method (Carlin & Chib 1995; Godsill 2001; Hee et al. 2016).”