×

Detecting abrupt changes by wavelet methods. (English) Zbl 1017.62033

Summary: The objective of this paper is to contribute to the methodology available for dealing with the detection and the estimation of the location of discontinuities in one-dimensional piecewise smooth regression functions observed in white Gaussian noise over an interval.
Our approach is nonparametric in nature because the unknown function is not assumed to have any specific form. Our method relies upon a wavelet analysis of the observed signal and belongs to the class of “indirect” methods, where one detects and locates the change points prior to fitting the curve, and then uses one’s favorite function estimation technique on each segment to recover the curve. We show that, provided discontinuities can be detected and located with sufficient accuracy, detection followed by wavelet smoothing enjoys optimal rates of convergence.

MSC:

62G08 Nonparametric regression and quantile regression
62G20 Asymptotic properties of nonparametric inference
62M09 Non-Markovian processes: estimation
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Abry P., Transformées en ondelettes -Analyses multirésolutions et signaux de pression en turbulance (1994)
[2] Andersson L., Recent Advances in Wavelet Analysis pp 1– (1993)
[3] Antoniadis A., Statistica Sinica 4 pp 651– (1994)
[4] Antoniadis, A. Invited talk ”Wavelet estimators for change-point regression models”. the conference on Splines and Wavelets in Statistics. May1995, Montréal, Canada. Vol. 18, pp.335–346. CRM - AMS Lecture Notes. 1999 · Zbl 0963.62032
[5] Antoniadis A., Detecting abrupt changes by wavelet methods (1997) · Zbl 1017.62033
[6] Bunt M., Kernel-based nonparametric regression for discontinuous functions (1995)
[7] DOI: 10.1109/TPAMI.1986.4767851
[8] DOI: 10.1006/acha.1993.1005 · Zbl 0795.42018
[9] DOI: 10.1093/biomet/65.2.243 · Zbl 0394.62074
[10] Daubechies I., Ten Lectures on Wavelets, CBMS-NSF Series in Applied Mathematics (1992) · Zbl 0776.42018
[11] DOI: 10.1093/biomet/81.3.425 · Zbl 0815.62019
[12] DOI: 10.1214/aos/1024691081 · Zbl 0935.62041
[13] DOI: 10.1214/lnms/1215463119
[14] DOI: 10.1023/A:1003802007064 · Zbl 0934.62035
[15] Girard D., Détection de discontinuités dans un signal par inf-convolution spline et validation croisée (1990)
[16] DOI: 10.2307/1268942
[17] Holschneider M., Wavelets: An Analysis Tool (1995)
[18] DOI: 10.1006/jmva.1998.1780 · Zbl 0962.62042
[19] Jaffard S., C. R. Acad. Sci. Paris 308 pp 79– (1989)
[20] DOI: 10.1137/1132110 · Zbl 0659.62103
[21] Laurent P. J., J. Approximation Theory and Its Applications 2 pp 71– (1986)
[22] DOI: 10.1109/TPAMI.1987.4767918
[23] DOI: 10.1214/aos/1032298290 · Zbl 0867.62033
[24] DOI: 10.2307/1270084 · Zbl 0651.62023
[25] DOI: 10.1109/34.192463 · Zbl 0709.94650
[26] DOI: 10.1109/18.119727 · Zbl 0745.93073
[27] DOI: 10.1007/BF01194493 · Zbl 0745.62048
[28] DOI: 10.2307/1269075 · Zbl 0626.65010
[29] DOI: 10.1214/aos/1176348654 · Zbl 0783.62032
[30] DOI: 10.1016/S0167-7152(96)00197-6 · Zbl 0874.62035
[31] DOI: 10.2307/3318530 · Zbl 0920.62053
[32] DOI: 10.1093/biomet/72.2.267 · Zbl 0571.60084
[33] Potier C., Curves Surfaces pp 477– (1994)
[34] DOI: 10.2307/1270648
[35] Raimondo M., Modèles de ruptures: situations non ergodiques et utilisations de méthodes d’ondelettes (1996)
[36] Speckman P. L., Detection of change-points in nonparametric regression (1994)
[37] DOI: 10.1093/biomet/82.2.385 · Zbl 0824.62031
[38] Wu J. S., Statistica Sinica 3 pp 557– (1993)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.