METODE REVERSIBLE JUMP MARKOV CHAIN MONTE CARLO UNTUK ESTIMASI BAYESIAN DALAM MODEL REGRESI LINEAR PER POTONGAN

Abstract

The method used to estimate the parameters of piecewise linear regression is Bayesian method. But the Bayes estimator can not be found analytically. To overcome these problems are proposed the Reversible Jump MCMC Algorithm. Reversible Jump MCMC Algorithm generates the Markov chain converges to the limit distribution of the posterior distribution of the parameters of piecewise linear regression models.Bayes estimator for the parameters of piecewise linear regression models obtained by the Markov chain.