friedman.1.data {tgp}R Documentation

First Friedman Dataset

Description

Function to generate X and Y values from the 10-dim “first” Friedman data set used to validate the Multivariate Adaptive Regression Splines (MARS) model. This function is stationary, with three non-linear and interacting variables, along with two linear, and five irrelevant effects.

Usage

friedman.1.data(n = 100)

Arguments

n Number of samples

Details

10-dim inputs X are drawn from N(0,1), and responses are N(m(X),1) where m(X) = E[X] and

E[X] = 10*sin(pi*X[,1]*X[,2]) + 20*(X[,3]-0.5)^2 + 10*X[,4] + 5*X[,5]

Value

Output is a data.frame with columns

X1...X10 describing the 10-d sampled inputs
Y sample responses (with N(0,1) noise)
Ytruth true responses (without noise)

Note

An example using this data is contained in the package vignette: vignette("tgp").

Author(s)

Robert B. Gramacy rbgramacy@ams.ucsc.edu

References

Friedman, J. H. (1991). Multivariate adaptive regression splines. “Annals of Statistics”, 19, No. 1, 1–67.

Gramacy, R. B., Lee, H. K. H. (2006). Bayesian treed Gaussian process models. Available as UCSC Technical Report ams2006-01.

Chipman, H., George, E., & McCulloch, R. (2002). Bayesian treed models. Machine Learning, 48, 303–324.

http://www.ams.ucsc.edu/~rbgramacy/tgp.html

See Also

tgp, bgpllm, btlm, blm, bgp, btgpllm bgp


[Package tgp version 1.1-11 Index]