Dynamic local models for segmentation and prediction of financial time series

Mehdi Azzouzi and Ian Nabney

The European Journal of Finance, 2001, vol. 7, issue 4, 289-311

Abstract: In the analysis and prediction of many real-world time series, the assumption of stationarity is not valid. Aspecial form of non-stationarity, where the underlying generator switches between (approximately) stationary regimes, seems particularly appropriate for financial markets. We introduce a new model which combines a dynamic switching (controlled by a hidden Markov model) and a non-linear dynamical system. We show how to train this hybrid model in a maximum likelihood approach and evaluate its performance on both synthetic and financial data.

Keywords: Time Series Segmentation Hidden Variational Techniques Bayesian Error Bars Markov Models State Space Models (search for similar items in EconPapers)
Date: 2001
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.tandfonline.com/doi/abs/10.1080/13518470110071155 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:eurjfi:v:7:y:2001:i:4:p:289-311

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/REJF20

DOI: 10.1080/13518470110071155

Access Statistics for this article

The European Journal of Finance is currently edited by Chris Adcock

More articles in The European Journal of Finance from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().