Bayesian Computation and Analysis of C-PAR(1) Time Series Model with Structural Break

Authors

  • Ashok Kumar Department of Statistics, Central University of Rajasthan, NH-8, Bandersindri, Ajmer, Rajasthan, India
  • Jitendra Kumar Department of Statistics, Central University of Rajasthan, NH-8, Bandersindri, Ajmer, Rajasthan, India
  • Varun Agiwal Department of Statistics, Central University of Rajasthan, NH-8, Bandersindri, Ajmer, Rajasthan, India

Keywords:

Bayesian inference, covariate, Gibbs sampler, panel data model, unit root test

Abstract

Panel data consists of repeated observations over time on the same set of cross-sectional units and impact of covariate may influence the estimation and testing procedures. Present paper proposes a covariate panel autoregressive (C-PAR(1)) unit root tests and estimation considering structural break under Bayesian approach. We use Monte Carlo simulation method to estimate the parameters using conditional posterior distribution and compared with ordinary least square estimator. For testing the unit root hypothesis, posterior odds ratio is derived and recorded satisfactory results. We have also studied empirical analysis on import of fertilizers to get more applicability of the model.

Downloads

Published

2020-03-20

How to Cite

Kumar, A. ., Kumar, J. ., & Agiwal, V. . (2020). Bayesian Computation and Analysis of C-PAR(1) Time Series Model with Structural Break. Thailand Statistician, 18(2), 150–164. Retrieved from https://ph02.tci-thaijo.org/index.php/thaistat/article/view/240226

Issue

Vol. 18 No. 2 (2020): April

Section

Articles