You are not currently logged in.
Access JSTOR through your library or other institution:
Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting
William S. Cleveland and Susan J. Devlin
Journal of the American Statistical Association
Vol. 83, No. 403 (Sep., 1988), pp. 596-610
Stable URL: http://www.jstor.org/stable/2289282
Page Count: 15
You can always find the topics here!Topics: Data smoothing, Simulations, Loess, Ozone, Linear regression, Statistics, Statistical estimation, Approximation, Hardness, Velocity
Were these topics helpful?See something inaccurate? Let us know!
Select the topics that are inaccurate.
Preview not available
Locally weighted regression, or loess, is a way of estimating a regression surface through a multivariate smoothing procedure, fitting a function of the independent variables locally and in a moving fashion analogous to how a moving average is computed for a time series. With local fitting we can estimate a much wider class of regression surfaces than with the usual classes of parametric functions, such as polynomials. The goal of this article is to show, through applications, how loess can be used for three purposes: data exploration, diagnostic checking of parametric models, and providing a nonparametric regression surface. Along the way, the following methodology is introduced: (a) a multivariate smoothing procedure that is an extension of univariate locally weighted regression; (b) statistical procedures that are analogous to those used in the least-squares fitting of parametric functions; (c) several graphical methods that are useful tools for understanding loess estimates and checking the assumptions on which the estimation procedure is based; and (d) the M plot, an adaptation of Mallow's Cp procedure, which provides a graphical portrayal of the trade-off between variance and bias, and which can be used to choose the amount of smoothing.
Journal of the American Statistical Association © 1988 American Statistical Association