![]() | Only 14 pages are availabe for public view |
Abstract The main objective of the current study is to handle the identification problem of autoregressive (AR) models from the Bayesian point of view. Two Bayesian identification approaches are considered. They are referred to as the direct and the indirect approaches. The two approaches are employed to the Bayesian identification process of AR models using three well known priors. These priors are the Natural- Conjugate prior, the Jeffrey’s prior and the G- prior. The theoretical derivations related to the two Bayesian identification approaches are conducted using the above mentioned three priors. Moreover, the performance of the two techniques, based on each of the three priors is investigated via comprehensive simulation studies Simulation results show that the two techniques are adequate in identifying AR models. The increase in the time series length leads to better performance for each technique Keywords: Autoregressive Models (AR); Bayesian Analysis; Time Series Analysi; Identification model; Posterior density; Direct Bayesian Identification; Indirect Bayesian Identification; Informative prior distribution; Non-informative prior distribution; G prior; Natural-Conjugate prior; Jeffreys’ prior. |