Multiscale breakpoint detection in piecewise stationary AR models

Cho, Haeran and Fryzlewicz, Piotr ORCID: 0000-0002-9676-902X (2008) Multiscale breakpoint detection in piecewise stationary AR models. In: IASC2008, 2008-12-05 - 2008-12-08, Yokohama, Japan, JPN. (Submitted)

Preview

PDF Download (207kB) | Preview

Abstract

In this paper, we are interested in the problem of detecting breakpoints in piecewise stationary autoregressive (AR) processes. For short time series, stationarity assumption is common. However, for longer time series, this assumption is often unrealistic. Besides, many naturally occurring phenomena cannot be modelled as stationary processes. Therefore modelling stochastic time series under nonstationary assumption is often appealing, and finnds its application in many areas, such as speech processing, biomedical signal processing, and seismology to name a few.

Item Type:	Conference or Workshop Item (Paper)
Official URL:	http://jasp.ism.ac.jp/~iasc2008/
Additional Information:	© 2008 The authors
Divisions:	Sociology
Subjects:	H Social Sciences > HA Statistics
Date Deposited:	11 Sep 2009 11:49
Last Modified:	12 Dec 2024 04:45
URI:	http://eprints.lse.ac.uk/id/eprint/25163

Actions (login required)

View Item