Open    Access



Bayesian Segmentation of Piecewise Linear Regression Models Using Reversible Jump MCMC Algorithm



Author(s)

Suparman
Michel Doisy

Full-Text PDF XML     4098 Views

DOI:10.17265/1934-7332/2015.01.003

Department of Mathematical Education, Faculty of Teacher Training and Education, Yogyakarta 55161, Indonesia
ENSEEIHT/TESA (Ecole Nationale Superieure Electronique Electrotechnique Informatique Hydraulique Telecommunications), Toulouse 31071, France

Piecewise linear regression models are very flexible models for modeling the data. If the piecewise linear regression models are matched against the data, then the parameters are generally not known. This paper studies the problem of parameter estimation of piecewise linear regression models. The method used to estimate the parameters of picewise linear regression models is Bayesian method. But the Bayes estimator can not be found analytically. To overcome these problems, the reversible jump MCMC (Marcov Chain Monte Carlo) algorithm is proposed. Reversible jump MCMC algorithm generates the Markov chain converges to the limit distribution of the posterior distribution of the parameters of picewise linear regression models. The resulting Markov chain is used to calculate the Bayes estimator for the parameters of picewise linear regression models.

Piecewise linear regression models, hierarchical bayesian, reversible jump MCMC.