Earth: Multivariate Adaptive Regression Splines (MARS)
The earth package is an implementation of
Multivariate Adaptive Regression Splines, commonly known as "MARS".
What is MARS?
MARS is a statistical technique for modeling data.
It's an extension to linear regression that captures
nonlinearities and interactions between variables.
gives a good overview.
Earth package for the R language.
Standalone C version for those who
want to call earth from their own software without requiring R.
A MATLAB interface is also provided (thanks to
This standalone version is based on earth version 3.2-6 (Nov 24, 2013).
General information on MARS
Wikipedia article (recommended)
Statsoft commercial vendor
Salford commercial vendor
Notes on the earth package document included with the R package
The earth source code is licensed under the GPL and runs in an R environment, or can be used as a stand-alone C library.
Earth is derived from the mda:mars library written by Trevor Hastie and Rob Tibshirani.
What people are using earth for
Earth is widely used.
Here's a small sample of what it's being used for.
(Note: This list was created in 2009 and is very out of date.)
Max Kuhn at
is using earth for building predictive models in
computational biology and chemistry.
You may also want to check out Max's
at the University of Tuebingen
(Institute of Geography) is using earth for Pedometrics / Digital Soil Mapping.
Trevor Nell at
Brolink (Pty) Ltd
is using earth to analyse insurance
claim data to determine appropriate premiums.
Kurt Salmela and Ming Shan of
are using earth for
analyzing marketing research survey data.
Darin Brooks at the
University of British Columbia
Kim Forest Management Ltd
is using earth for predicting secondary growth/mid-term timber supply
in the BC forestry sector.
Internal data structures
Internal call graphs
The following people have contributed to
the earth package in one way or another.
I apologize to anyone that I may have inadvertently omitted.
Ana Ruize Navarro,
Dylan R Harp,
Esteban Alfaro Cortes,
Eugene Shaine Mednikov,
Hamid Reza Pourghasemi,
Lara E Bauman,
Marko Robnik Sokonja,
Pierric de Laborie,
Thomas A Brandenburger,
To Stephen Milborrow Homepage