Reversible-jump Markov chain Monte Carlo

Reversible-jump Markov Chain Monte Carlo (RJMCMC) is a statistical method used for Bayesian inference in models where the dimensionality of the parameter space can change. This is particularly useful in variable selection problems or model selection problems where different models may have different numbers of parameters. The key idea of RJMCMC is to allow the Markov chain to jump between models of different dimensions.