Bayesian model of time series with multiple change points, censured observations and autoregressive segments of order one (AR(1))

Authors

  • Rene Castro-Montoya
  • Gabriel Arcangel Rodriguez-Yam
  • Felipe de Jesus Peraza-Garay
  • Jose Vidal Jimenez-Ramirez
  • Mario Castro-Flores Estadistica

DOI:

https://doi.org/10.46932/sfjdv3n2-083

Keywords:

parameter estimation, bayesian inference, prior distributions, metropolis algorithm, reversible jump markov chain monte carlo algorithm.

Abstract

A Bayesian model for a nonstationary time series with an unknown number of change points and censored observations where each piece is assumed to be an autoregressive process of order unknown is considered in this paper. To estimate the number and localizations of the unknown change points the Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm developed by [green95] is used. The censured problem is solved by the method of [jungetal05] by imputing the censured values from a multivariate normal distribution given the observed part.

Published

2022-04-08