Full Bayesian analysis of double seasonal autoregressive models with real applications

• Published in: Journal of applied statistics Vol. 51; no. 8; pp. 1524 - 1544
• Main Author: Amin, Ayman A.
• Format: Journal Article
• Language: English
• Published: England Taylor & Francis 10.06.2024; Taylor & Francis Ltd
• Subjects: Algorithms; Autoregressive models; Bayesian analysis; DSAR models; Electrical loads; hourly electricity load; Mixtures; multiple seasonality; posterior analysis; Predictions; predictive analysis; Statistical methods; 62M10; multiple seasonality; posterior analysis; hourly electricity load; DSAR models; 62F15; predictive analysis

We present a full Bayesian analysis of multiplicative double seasonal autoregressive (DSAR) models in a unified way, considering identification (best subset selection), estimation, and prediction problems. We assume that the DSAR model errors are normally distributed and introduce latent variables f...