统计学与应用  >> Vol. 4 No. 4 (December 2015)

基于双边核估计的保持跳跃曲线回归过程
A Jump-Preserving Curve Regression Procedure Based on Bilateral Kernel Estimation

DOI: 10.12677/SA.2015.44037, PDF, HTML, XML, 下载: 1,521  浏览: 4,777  国家自然科学基金支持

作者: 李怡然, 黄性芳*, 丁嘉沼, 陈旋:东南大学数学系,江苏 南京

关键词: 曲线拟合保持跳跃双边核估计加权残差平方和不连续曲线Curve Fitting Procedure Jump-Preserving Bilateral Kernel Estimation Weighted Residual Sums of Squares Discontinuous Curve

摘要: 跳跃曲线回归在某些实际问题中非常重要,但是由于数据采集过程中受到噪声的干扰,传统的曲线回归方法对于跳跃位置的保持效果欠佳。本文基于分段双边核估计提出了一个保持跳跃的曲线拟合过程。该过程不仅在x方向上用核函数进行加权,亦在y方向上使用核函数。在目标点的邻域内,分别在左半邻域、右半邻域和全邻域对函数进行估计,并计算加权残差平方和以进行比较,选取较小的加权残差平方和的一个作为目标点的最终估计,以此来达到无需提前探测跳跃点的同时保持曲线跳跃特性的目的。数值模拟和实际数据分析表明该方法的可行性和有效性。
Abstract: It is well known that curve regression is very important in many applications. However, since data collection procedures are disturbed by errors, traditional curve regression methods cannot play well in jump points. This paper proposes a jump-preserving curve fitting procedure, which is based on bilateral kernel estimation. Kernel functions are not only added to x-axis, but also added to y-axis. Then, we estimate given points from left side, right side and whole neighborhood. Weighted residual sums of squares are calculated to compare. The estimate with smaller weighted residual sums of squares is selected as the final estimate of the given point, so that we can achieve jump- preserving while not to detect jump points at first. Numerical simulation and real data analysis demonstrate the feasibility and efficiency of this method.

文章引用: 李怡然, 黄性芳, 丁嘉沼, 陈旋. 基于双边核估计的保持跳跃曲线回归过程[J]. 统计学与应用, 2015, 4(4): 335-347. http://dx.doi.org/10.12677/SA.2015.44037

参考文献

[1] Müller, H.-G. (1992) Change-Points in Nonparametric Regression Analysis. The Annuals of Statistics, 20, 737-761.
http://dx.doi.org/10.1214/aos/1176348654
[2] Qiu, P., Cho, A. and Li, X. (1991) Estimation of Jump Regression Functions. Bulletin of Information and Cybernetics, 24, 197-212.
[3] Wu, J.S. and Chu, C.K. (1993) Kernel Type Es-timators of Jump Points and Values of a Regression Function. The Annals of Statistics, 21, 1545-1566.
http://dx.doi.org/10.1214/aos/1176349271
[4] Loader, C.R. (1996) Change Point Estimation Using Nonparametric Regression. The Annals of Statistics, 24, 1667- 1678.
http://dx.doi.org/10.1214/aos/1032298290
[5] Qiu, P. and Yandell, B.(1998) A Local Polynomial Jump Detection Algorithm in Nonparametric Regression. Technometrics, 40, 141-152.
[6] Wang, Y. (1995) Jump and Sharp Cusp Detection by Wavelets. Biometrika, 82, 385-397.
http://dx.doi.org/10.1093/biomet/82.2.385
[7] Eubank, R.L. and Speckman, P.L. (1994) Nonparametric Estimation of Functions with Jump Discontinuities. In: Carlstein, E., Müller, H.G. and Siegmund, D., Eds., IMS Lecture Notes, Vol. 23, Change-Point Problems, 130-144.
http://dx.doi.org/10.1214/lnms/1215463119
[8] Koo, J.Y. (1997) Spline Estimation of Discontinuous Regression Functions. Journal of Computational and Graphical Statistics, 6, 266-284.
[9] Shiau, J.H., Wahba, G. and Johnson, D.R. (1986) Partial Spline Models for the Inclusion of Tropopause and Frontal Boundary Information in Otherwise Smooth Two- and Three-Dimensional Objective Analysis. Journal of Atmospheric and Oceanic Technology, 3, 714-725.
http://dx.doi.org/10.1175/1520-0426(1986)003<0714:PSMFTI>2.0.CO;2
[10] McDonald, J.A. and Owen, A.B. (1986) Smoothing with Split Linear Fits. Technometrics, 28, 195-208.
http://dx.doi.org/10.1080/00401706.1986.10488127
[11] Qiu, P. (2003) A Jump-Preserving Curve Fitting Proce-dure Based on Local Piecewise-Linear Kernel Estimation. Jour- nal of Nonparametric Statistics, 15, 437-453.
http://dx.doi.org/10.1080/10485250310001595083
[12] Fan, J. and Gijbels, I. (1996) Local Polynomial Modeling and Its Applications. Chapman & Hall, London, 66.
[13] Wikipedia, Kernel (Statistics). https://en.wikipedia.org/wiki/Kernel_(statistics)
[14] Silverman, B.W. (1986) Density Estimation for Statistics and Data Analysis. Chapman & Hall, London, 39, 296-297.
http://dx.doi.org/10.1007/978-1-4899-3324-9
[15] Nadaraya, E.A. (1964) On Estimating Regression. Theory of Probability & Its Applications, 9, 141-142.
http://dx.doi.org/10.1137/1109020
[16] Qiu, P. (1994) Estimation of the Number of Jumps of the Jump Regression Functions. Communications in Statistics-Theory and Methods, 23, 2141-2155.
http://dx.doi.org/10.1080/03610929408831378
[17] Finance.yahoo.com. CEA Weekly-Adjusted Close Price. http://finance.yahoo.com/q/hp?s=CEA+Historical+Prices
[18] Loader, C.R. (1999) Bandwidth Selection: Classical or Plug-In? Annals of Statistics, 27, 415-438.
http://dx.doi.org/10.1214/aos/1018031201