A Bayesian Approach to Robust Skewed Autoregressive Processes

Abstract This article studies autoregressive (AR) models assuming innovations with scale mixtures of skew-normal (SMSN) distributions, an attractive and flexible family of probability distributions. A Bayesian analysis considering informative prior distributions is presented. Comprehensive simulatio...

Full description

Saved in:
Bibliographic Details
Published inBulletin - Calcutta Statistical Association Vol. 69; no. 2; pp. 165 - 182
Main Authors Maleki, Mohsen, Arellano-Valle, Reinaldo B., Dey, Dipak K., Mahmoudi, Mohammad R., Jalali, Seyed Mohammad J.
Format Journal Article
LanguageEnglish
Published New Delhi, India SAGE Publications 01.11.2017
Subjects
SMSN distributions
non-Gaussian time series
Autoregressive models
Gibbs sampling
MCMC method
Online AccessGet full text

Cover

More Information
Summary:Abstract This article studies autoregressive (AR) models assuming innovations with scale mixtures of skew-normal (SMSN) distributions, an attractive and flexible family of probability distributions. A Bayesian analysis considering informative prior distributions is presented. Comprehensive simulation studies are performed to support the performance of the proposed model and methods. The proposed methods are also applied on a real-time series data which has previously been analysed under Gaussian and Student-t AR models.
ISSN:0008-0683
2456-6462
DOI:10.1177/0008068317732196