Adaptive trend estimation in financial time series via multiscale change-point-induced basis recovery

Schroeder, Anna Louise and Fryzlewicz, Piotr ORCID: 0000-0002-9676-902X (2013) Adaptive trend estimation in financial time series via multiscale change-point-induced basis recovery. Statistics and Its Interface, 6 (4). pp. 449-461. ISSN 1938-7997

Preview

PDF - Published Version Download (1MB) | Preview

Abstract

Low-frequency financial returns can be modelled as centered around piecewise-constant trend functions which change at certain points in time. We propose a new stochastic time series framework which captures this feature. The main ingredient of our model is a hierarchically-ordered oscillatory basis of simple piecewise-constant functions. It differs from the Fourier-like bases traditionally used in time series analysis in that it is determined by change-points, and hence needs to be estimated from the data before it can be used. The resulting model enables easy simulation and provides interpretable decomposition of nonstationarity into short- and long-term components. The model permits consistent estimation of the multiscale change-point-induced basis via binary segmentation, which results in a variablespan moving-average estimator of the current trend, and allows for short-term forecasting of the average return.

Item Type:	Article
Official URL:	http://dx.doi.org/10.4310/SII.2013.v6.n4.a4
Additional Information:	© 2013 International Press of Boston, Inc.
Divisions:	Statistics
Subjects:	H Social Sciences > HG Finance Q Science > QA Mathematics
JEL classification:	G - Financial Economics > G0 - General
Date Deposited:	16 Dec 2013 14:00
Last Modified:	06 Nov 2024 23:39
Funders:	Economic and Social Research Council
URI:	http://eprints.lse.ac.uk/id/eprint/54934

Actions (login required)

View Item