Abstract
This paper deals with nonparametric estimation of a regression curve, where the estimation method should preserve possible jumps in the curve. At each point x at which one wants to estimate the regression function, the method chooses in an adaptive way among three estimates: a local linear estimate using only datapoints to the left of x, a local linear estimate based on only datapoints to the right of x, and finally a local linear estimate using data in a two-sided neighbourhood around x. The choice among these three estimates is made by looking at differences of the weighted residual mean squares of the three fits. The resulting estimate preserves the jumps well and in addition gives smooth estimates of the continuity parts of the curve. This property of compromise between local smoothing and jump-preserving is what distinguishes our method from most previously proposed methods, that mainly focused on local smoothing and consequently blurred possible jumps, or mainly focused on jump-preserving and hence led to rather noisy estimates in continuity regions of the underlying regression curve. Strong consistency of the estimator is established and its performance is tested via a simulation study. This study also compares the current method with some existing methods. The current method is illustrated in analyzing a real dataset.
Similar content being viewed by others
References
Chu C.-K., Glad I.K., Godtliebsen F., Marron J.S. (1998). Edge preserving smoothers for image processing (with discussion). Journal of the American Statistical Association 93:526–556
Eubank R.L., Speckman P.L. (1994). Nonparametric estimation of functions with jump discontinuities. In: Carlstein E., Müller H.-G. Siegmund D. (eds) Change-point Problems, IMS–Lecture Notes, (Vol. 23, pp 130–143).
Fan J., Gijbels I. (1996). Local polynomial modelling and its applications. Chapman and Hall, New York
Gijbels I., Goderniaux A.-C. (2004). Bandwidth selection for change point estimation in nonparametric regression. Technometrics 46:76–86
Gijbels I., Hall P., Kneip A. (1999). On the estimation of jump points in smooth curves. The Annals of the Institute of Statistical Mathematics 51:231–251
Grégoire G., Hamrouni Z. (2002). Change-point estimation by local linear smoothing. Journal of Multivariate Analysis 83:56–83
Hall P., Titterington D.M. (1992). Edge preserving and peak-preserving smoothing. Technometrics 34:429–440
Hamrouni Z. (1999). Inférence statistique par lissage linéaire local pour une fonction de régression présentant des discontinuités. Doctoral Dissertation, Université de Joseph Fourier, Grenoble, France
Kang K.H., Koo J.Y., Park C.W. (2000). Kernel estimation of discontinuous regression functions. Statistics and Probability Letters 47:277–285
Koo J.Y. (1997). Spline estimation of discontinuous regression functions. Journal of Computational and Graphical Statistics 6:266–284
Lee J.S. (1983). Digital image smoothing and the sigma filter. Computer Vision, Graphics and image Processing 24:255–269
Masry E. (1996). Multivariate local polynomial regression for time series: uniform strong consistency and rates. Journal of Time Series Analysis 17:571–599
Mc Donald J.A., Owen A.B. (1986). Smoothing with linear fits. Technometrics 28:195–208
Müller H.-G. (1992). Change-points in nonparametric regression analysis. The Annals of Statistics 20:737–761
Müller H.-G., Song K.-S. (1997). Two-stage change-point estimators in smooth regression models. Statistics and Probability Letters 34:323–335
Polzehl J., Spokoiny V.G. (2000). Adaptative weights smoothing with applications to image restoration. Journal of the Royal Statistical Society, Series B 2:335–354
Polzehl, J., Spokoiny, V. G. (2003). Varying coefficient regression modeling by adaptive weights smoothing. WIAS-Preprint 818 , Berlin.
Qiu P. (2003). A jump-preserving curve fitting procedure based on local piecewise-linear kernel estimation. Journal of Nonparametric Statistics 15:437–453
Qiu P., Yandell B. (1998). A local polynomial jump detection algorithm in nonparametric regression. Technometrics 40:141–152
Rue H., Chu C.-K., Godtliebsen F., Marron J.S. (2002). M-smoother with local linear fit. Journal of Nonparametric Statistics 14:155–168
Scott D.W. (1992). Multivariate density estimation. Theory, practice and visualization. Wiley, New York
Speckman, P. L. (1994). Detection of change-points in nonparametric regression. Unpublished manuscript
Spokoiny V.G. (1998). Estimation of a function with discontinuities via local polynomial fit with an adaptive window choice. The Annals of Statistics 26:1356–1378
Wu J.S., Chu C.K. (1993). Kernel type estimators of jump points and values of a regression function. The Annals of Statistics 21:1545–1566
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Gijbels, I., Lambert, A. & Qiu, P. Jump-Preserving Regression and Smoothing using Local Linear Fitting: A Compromise. AISM 59, 235–272 (2007). https://doi.org/10.1007/s10463-006-0045-9
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-006-0045-9