Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

Weighted Local Regression and Kernel Methods for Nonparametric Curve Fitting

Hans-Georg Muller
Journal of the American Statistical Association
Vol. 82, No. 397 (Mar., 1987), pp. 231-238
DOI: 10.2307/2289159
Stable URL: http://www.jstor.org/stable/2289159
Page Count: 8
  • Download ($14.00)
  • Cite this Item
Weighted Local Regression and Kernel Methods for Nonparametric Curve Fitting
Preview not available

Abstract

Weighted local regression, a popular technique for smoothing scatterplots, is shown to be asymptotically equivalent to certain kernel smoothers. Since both methods are local weighted averages of the data, it is proved that in the fixed design regression model, given a weighted local regression procedure with any weight function, there is a corresponding kernel method such that the quotients of weights distributed by both methods tend uniformly to 1 as the number of observations increases to infinity. It is demonstrated by examples that in some instances the weights are nearly the same for both methods, even for small samples. The asymptotic equivalence allows the derivation of the leading terms of the mean squared error and of the local limit distribution for weighted local regression. Further, a close correspondence is found between the orders of the polynomial to be locally fitted in weighted local regression and the order (number of vanishing moments) of the kernel employed in the kernel smoother and between the shapes of the kernel and the weight function.

Page Thumbnails

  • Thumbnail: Page 
231
    231
  • Thumbnail: Page 
232
    232
  • Thumbnail: Page 
233
    233
  • Thumbnail: Page 
234
    234
  • Thumbnail: Page 
235
    235
  • Thumbnail: Page 
236
    236
  • Thumbnail: Page 
237
    237
  • Thumbnail: Page 
238
    238