Scholarlink

We introduce a novel framework for multivariate time series that demonstrates the powerful synergy between MIxed-DAta Sampling (MIDAS) and Markov-switching models. Specifically, we derive a general multivariate hidden semi-Markov model with configuration of latent states that is not known in advance. Bayesian inference is performed by means of a Reversible Jump Markov Chain Monte Carlo algorithm. We illustrate with a real data application on the association between energy consumption, production, and prices.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bayesian Multivariate Semi-Markov-Switching MIxed DAta Sampling (MIDAS) Regression with Unknown Configuration of Hidden Regimes

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Alfonso Russo,
  • Antonello Maruotti,
  • Alessio Farcomeni

摘要

We introduce a novel framework for multivariate time series that demonstrates the powerful synergy between MIxed-DAta Sampling (MIDAS) and Markov-switching models. Specifically, we derive a general multivariate hidden semi-Markov model with configuration of latent states that is not known in advance. Bayesian inference is performed by means of a Reversible Jump Markov Chain Monte Carlo algorithm. We illustrate with a real data application on the association between energy consumption, production, and prices.