Estimation of linear autoregressive models with Markov-switching, the E.M. algorithm revisited

TL;DR

This paper revisits the EM algorithm for estimating linear autoregressive models with Markov-switching, generalizing Elliot's method for hidden Markov models and simplifying the computation by avoiding backward recursion.

Contribution

The paper introduces a generalized EM algorithm for Markov-switching autoregressive models that eliminates the need for backward recursion, simplifying the estimation process.

Findings

The new method effectively estimates model parameters.

It simplifies computation compared to previous approaches.

The approach generalizes existing methods for hidden Markov models.

Abstract

This work concerns estimation of linear autoregressive models with Markov-switching using expectation maximisation (E.M.) algorithm. Our method generalise the method introduced by Elliot for general hidden Markov models and avoid to use backward recursion.