作者: Jerome H. Friedman , Bernard W. Silverman
DOI: 10.1080/00401706.1989.10488470
关键词: Simple (abstract algebra) 、 Curve fitting 、 Noise 、 Mathematics 、 Cross-validation 、 Smoothing 、 Regression analysis 、 Nonlinear system 、 Piecewise linear function 、 Econometrics
摘要: A simple method is presented for fitting regression models that are nonlinear in the explanatory variables. Despite its simplicity—or perhaps because of it—the has some powerful characteristics cause it to be competitive with and often superior more sophisticated techniques, especially small data sets presence high noise.