Multivariate Adaptive Regression Splines
Author:
- 29 September 2014
- book chapter
- Published by Wiley
Abstract
The multivariate adaptive regression splines (MARS) algorithm was developed by Friedman as a nonparametric method for multiple regression. The MARS algorithm uses adaptively selected spline functions. Because of its adaptivity MARS is often able to model functions that express high variation in one region of the predictor space and are smoother in other parts.Keywords
This publication has 14 references indexed in Scilit:
- Polynomial splines and their tensor products in extended linear modeling: 1994 Wald memorial lectureThe Annals of Statistics, 1997
- Polychotomous RegressionJournal of the American Statistical Association, 1997
- Hazard RegressionJournal of the American Statistical Association, 1995
- Logspline Density Estimation for Censored DataJournal of Computational and Graphical Statistics, 1992
- A study of logspline density estimationComputational Statistics & Data Analysis, 1991
- Multivariate Adaptive Regression SplinesThe Annals of Statistics, 1991
- Flexible Parsimonious Smoothing and Additive ModelingTechnometrics, 1989
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978
- A Practical Guide to Splines1978
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974