Time‐Varying Transition Probabilities for Markov Regime Switching Models

We propose a new Markov switching model with time‐varying transitions probabilities. The novelty of our model is that the transition probabilities evolve over time by means of an observation driven model. The innovation of the time‐varying probability is generated by the score of the predictive like...

Full description

Saved in:
Bibliographic Details
Published in:Journal of time series analysis 2017-05, Vol.38 (3), p.458-478
Main Authors: Bazzi, Marco, Blasques, Francisco, Koopman, Siem Jan, Lucas, Andre
Format: Article
Language:English
Subjects:
Estimating techniques
Hidden Markov models
Monte Carlo simulation
observation driven models
Studies
Time series
time varying parameter
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a new Markov switching model with time‐varying transitions probabilities. The novelty of our model is that the transition probabilities evolve over time by means of an observation driven model. The innovation of the time‐varying probability is generated by the score of the predictive likelihood function. We show how the model dynamics can be readily interpreted. We investigate the performance of the model in a Monte Carlo study and show that the model is successful in estimating a range of different dynamic patterns for unobserved regime switching probabilities. We also illustrate the new methodology in an empirical setting by studying the dynamic mean and variance behaviour of US industrial production growth.
ISSN:0143-9782
1467-9892
DOI:10.1111/jtsa.12211