Advanced

Stylised facts of financial time series and hidden Markov models in continuous time

Peter, Nystrup; Henrik, Madsen and Lindström, Erik LU (2015) In Quantitative Finance 15(9). p.1531-1541
Abstract
Hidden Markov models are often applied in quantitative finance to capture the stylised facts of financial returns. They are usually discrete-time models and the number of states rarely exceeds two because of the quadratic increase in the number of parameters with the number of states. This paper presents an extension to continuous time where it is possible to increase the number of states with a linear rather than quadratic growth in the number of parameters. The possibility of increasing the number of states leads to a better fit to both the distributional and temporal properties of daily returns.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Hidden Markov models, Continuous time, Daily returns, Leptokurtosis, Volatility clustering, Long memory, C01—Econometrics, C16—Specific distributions, C22—Time-series models, C52—Model evaluation and testing
in
Quantitative Finance
volume
15
issue
9
pages
1531 - 1541
publisher
Taylor & Francis
external identifiers
  • wos:000359743900003
  • scopus:84938741594
ISSN
1469-7696
DOI
10.1080/14697688.2015.1004801
language
English
LU publication?
yes
id
b739cc33-85e2-4dd8-810d-22bfa4ab4458 (old id 5049458)
alternative location
http://www.tandfonline.com/doi/full/10.1080/14697688.2015.1004801#abstract
date added to LUP
2015-02-13 14:03:24
date last changed
2017-02-08 13:39:13
@article{b739cc33-85e2-4dd8-810d-22bfa4ab4458,
  abstract     = {Hidden Markov models are often applied in quantitative finance to capture the stylised facts of financial returns. They are usually discrete-time models and the number of states rarely exceeds two because of the quadratic increase in the number of parameters with the number of states. This paper presents an extension to continuous time where it is possible to increase the number of states with a linear rather than quadratic growth in the number of parameters. The possibility of increasing the number of states leads to a better fit to both the distributional and temporal properties of daily returns.},
  author       = {Peter, Nystrup and Henrik, Madsen and Lindström, Erik},
  issn         = {1469-7696},
  keyword      = {Hidden Markov models,Continuous time,Daily returns,Leptokurtosis,Volatility clustering,Long memory,C01—Econometrics,C16—Specific distributions,C22—Time-series models,C52—Model evaluation and testing},
  language     = {eng},
  number       = {9},
  pages        = {1531--1541},
  publisher    = {Taylor & Francis},
  series       = {Quantitative Finance},
  title        = {Stylised facts of financial time series and hidden Markov models in continuous time},
  url          = {http://dx.doi.org/10.1080/14697688.2015.1004801},
  volume       = {15},
  year         = {2015},
}