Nonparametric Splitting Algorithm for Detecting Structural Changes in Predictive Relationships
Pages 143 - 149
Abstract
The problem of detecting structural changes in a regression study has become crucially important in a wide variety of fields, since data generating processes in a real world are usually unstable. Taking into account the fact that relationships within observed data are often in a continuous flux, it can be challenging to make any distributional assumptions. In the current paper, we propose a new nonparametric technique which allows estimation of an unknown number of structural change points in multivariate data having univariate response. The Nonparametric Splitting algorithm is a heuristic smart search for relationship changes based on a consequential division of the data into smaller parts. The approach utilizes a nonparametric change point test to find narrow regions of change locations. Our preliminary experiments are promising and suggest potential for the high efficiency and prediction accuracy of the introduced method.
References
[1]
A.L.Schröder, P. Fryzlewicz, Adaptive trend estimation in financial time series via multiscale change-point-induced basis recovery, Statistics and Its Interface 6. 449--461, (2013)
[2]
V.N. Minin, K.S. Dorman, F. Fang, M.A. Suchard, Dual multiple change-point model leads to more accurate recombination detection, Bioinformatics. 3034--3042, (2005)
[3]
C. Gallagher, R. Lund, M. Robbins, Changepoint Detection in Climate Time Series with Long-Term Trends, Journal of Climate 26. 4994--5006, (2013)
[4]
E.S. Page, Continuous inspection schemes, Biometrika. 100--115, (1954)
[5]
Z. Harchaoui, C. Levy-Leduc, Multiple Change-Point Estimation With a Total Variation Penalty, Journal of the American Statistical Association. 1480--1493, (2010)
[6]
R.A. Davis, T.C.M. Lee, G.A. Rodriguez-Yam, Break Detection for a Class of Nonlinear Time Series Models, Journal of Time Series Analysis. 834--867, 2008
[7]
M. Lavielle, E. Moulines, Least-squares Estimation of an Unknown Number of Shifts in a Time Series, Journal of Time Series Analysis. 33--59, (2000)
[8]
E. Lebarbier, Detecting multiple change-points in the mean of Gaussian process by model selection, Signal Processing 85. 717--736, (2005)
[9]
M. Kolar, L. Song, E.P. Xing, Sparsistent learning of varying-coefficient models with structural changes, Advances in neural information processing systems, 1006--1014, (2009)
[10]
H. Cho, P. Fryzlewicz, Multiple change-point detection for high-dimensional time series via Sparsified Binary Segmentation, Journal of the Royal Statistical Society Series B. 475--507, 2015
[11]
J. Bai, P. Perron, Estimating and Testing Linear Models with Multiple Structural Changes, Econometrica. 47--78, (1998) P.E. Ferreira, A Bayesian analysis of a switching regression model: Known number of regimes, Journal of the American Statistical Association, 70, 370--374, (1975)
[12]
G. Shcwartz, Estimating the dimension of a model, Annals of Statistics, 461--464, (1978)
[13]
R.L. Brown, J. Durbin, J.M. Evans, Techniques for testing the constancy of regression relationships over time (with discussion), Journal of the Royal Statistical Society B, 149--192, (1975)
[14]
T. Hastie, J.C. Wang, Boosted varying-coefficient regression models for product demand prediction, Journal of Computational and Graphical Statistics. 361--382, (2014)
[15]
D.S. Matteson, N.A. James, A nonparametric approach for multiple change point analysis of multivariate data, Journal of the American Statistical Association. 334--345, (2014)
[16]
A. Khaleghi, D. Ryabko, Nonparametric multiple change point estimation in highly dependent time series, Algorithmic Learning Theory. 382--396, (2013)
[17]
M.L. Rizzo, G.J. Székely Disco Analysis: A Nonparametric Extension of Analysis of Variance, The Annals of Applied Statistics. 1034--1055, (2010).
Index Terms
- Nonparametric Splitting Algorithm for Detecting Structural Changes in Predictive Relationships
Recommendations
Abrupt change in mean using block bootstrap and avoiding variance estimation
We deal with sequences of weakly dependent observations that are naturally ordered in time. Their constant mean is possibly subject to change at most once at some unknown time point. The aim is to test whether such an unknown change has occurred or not. ...
Nonparametric likelihood ratio goodness-of-fit tests for survival data
Berk and Jones (Z. Wahrsch. Verw. Gebiete 47 (1979) 47) described a nonparametric likelihood test of uniformity that is more efficient, in Bahadur's sense, than any weighted Kolmogorov-Smirnov test at any alternative. This article shows how to obtain a ...
Comments
Information & Contributors
Information
Published In
May 2017
307 pages
ISBN:9781450352413
DOI:10.1145/3093241
Copyright © 2017 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- University of Florida: University of Florida
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 19 May 2017
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICCDA '17
ICCDA '17: 2017 International Conference on Compute and Data Analysis
May 19 - 23, 2017
FL, Lakeland, USA
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 57Total Downloads
- Downloads (Last 12 months)3
- Downloads (Last 6 weeks)1
Reflects downloads up to 27 Jul 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in