An infinite hidden Markov model with stochastic volatility
Journal of Forecasting · 2024-09 · 43 (6) · 2187-2211
DOI: 10.1002/for.3123 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Forecasting, online erschienen am 02.04.2024. Verfasst von Chenxing Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Social Sciences and Humanities Research Council of Canada, National Natural Science Foundation of China, Philosophy and Social Science Foundation of Hunan Province.
Abstract (Originalsprache)
This paper extends the Bayesian semiparametric stochastic volatility (SV‐DPM) model. Instead of using a Dirichlet process mixture (DPM) to model return innovations, we use an infinite hidden Markov model (IHMM). This allows for time variation in the return density beyond that attributed to parametric latent volatility. The new model nests several special cases as well as the SV‐DPM. We also discuss posterior and predictive density simulation methods for the model. Applied to equity returns, foreign exchange rates, oil price growth and industrial production growth, the new model improves density forecasts, compared with the SV‐DPM, a stochastic volatility with Student's innovations and other fat‐tailed volatility models.
Förderung
- Social Sciences and Humanities Research Council of Canada
- National Natural Science Foundation of China
- Philosophy and Social Science Foundation of Hunan Province
Zitieren
APA
Li, C., Maheu, J. M., & Yang, Q. (2024). An infinite hidden Markov model with stochastic volatility. Journal of Forecasting, 43(6), 2187-2211. https://doi.org/10.1002/for.3123
Vancouver
Li C, Maheu JM, Yang Q. An infinite hidden Markov model with stochastic volatility. Journal of Forecasting. 2024;43(6):2187-2211. doi:10.1002/for.3123
BibTeX
@article{Li2024,
author = {Li, Chenxing and Maheu, John M. and Yang, Qiao},
title = {An infinite hidden Markov model with stochastic volatility},
journal = {Journal of Forecasting},
year = {2024},
volume = {43},
number = {6},
pages = {2187--2211},
doi = {10.1002/for.3123}
}
EUVIMED