WILD BINARY SEGMENTATION FOR MULTIPLE CHANGE-POINT DETECTION

被引:482
作者
Fryzlewicz, Piotr [1 ]
机构
[1] London Sch Econ, Dept Stat, London WC2A 2AE, England
基金
英国工程与自然科学研究理事会;
关键词
Multiple change-points; change-point detection; binary segmentation; randomised algorithms; thresholding; Bayesian information criterion; LEAST-SQUARES ESTIMATION; NUMBER; ALGORITHMS; SEQUENCE; INFORMATION; CRITERION; SELECTION; MODEL;
D O I
10.1214/14-AOS1245
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We propose a new technique, called wild binary segmentation (WBS), for consistent estimation of the number and locations of multiple change-points in data. We assume that the number of change-points can increase to infinity with the sample size. Due to a certain random localisation mechanism, WBS works even for very short spacings between the change-points and/or very small jump magnitudes, unlike standard binary segmentation. On the other hand, despite its use of localisation, WBS does not require the choice of a window or span parameter, and does not lead to a significant increase in computational complexity. WBS is also easy to code. We propose two stopping criteria for WBS: one based on thresholding and the other based on what we term the 'strengthened Schwarz information criterion'. We provide default recommended values of the parameters of the procedure and show that it offers very good practical performance in comparison with the state of the art. The 'WBS methodology is implemented in the R package wbs, available on CRAN. In addition, we provide a new proof of consistency of binary segmentation with improved rates of convergence, as well as a corresponding result for WBS.
引用
收藏
页码:2243 / 2281
页数:39
相关论文
共 55 条
[1]  
[Anonymous], 1993, MATH ITS APPL, DOI DOI 10.1007/978-94-015-8163-9
[2]   Testing for multiple change points [J].
Antoch, Jaromir ;
Jaruskova, Daniela .
COMPUTATIONAL STATISTICS, 2013, 28 (05) :2161-2183
[3]  
AUGER IE, 1989, B MATH BIOL, V51, P39, DOI 10.1007/BF02458835
[4]   Computation and analysis of multiple structural change models [J].
Bai, J ;
Perron, P .
JOURNAL OF APPLIED ECONOMETRICS, 2003, 18 (01) :1-22
[5]   Estimating multiple breaks one at a time [J].
Bai, JS .
ECONOMETRIC THEORY, 1997, 13 (03) :315-352
[6]  
BARANOWSKI R., 2014, WBS WILD BINARY SEGM
[7]  
Birge L., 2001, J. Eur. Math. Soc, P203
[8]   CONSISTENCIES AND RATES OF CONVERGENCE OF JUMP-PENALIZED LEAST SQUARES ESTIMATORS [J].
Boysen, Leif ;
Kempe, Angela ;
Liebscher, Volkmar ;
Munk, Axel ;
Wittich, Olaf .
ANNALS OF STATISTICS, 2009, 37 (01) :157-183
[9]  
Braun JV, 1998, STAT SCI, V13, P142
[10]   DETECTION WITH THE SCAN AND THE AVERAGE LIKELIHOOD RATIO [J].
Chan, Hock Peng ;
Walther, Guenther .
STATISTICA SINICA, 2013, 23 (01) :409-428