Bayesian Transformed GARMA Models

TL;DR

This paper introduces a Bayesian extension to TGARMA models, enhancing their ability to handle complex real-time series data with non-normality and heteroscedasticity, supported by simulations and real data analysis.

Contribution

It develops a Bayesian framework for TGARMA models, providing new estimation and model selection methods for improved analysis of complex time series.

Findings

Bayesian estimation performs well in simulations

Model selection criteria are effective

Real data analysis demonstrates practical utility

Abstract

Transformed Generalized Autoregressive Moving Average (TGARMA) models were recently proposed to deal with non-additivity, non-normality and heteroscedasticity in real time series data. In this paper, a Bayesian approach is proposed for TGARMA models, thus extending the original model. We conducted a simulation study to investigate the performance of Bayesian estimation and Bayesian model selection criteria. In addition, a real dataset was analysed using the proposed approach.