Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

plot.varmod

Plot a varmod object (created by calling earth with the varmod argument)


Description

Plot a variance model (a varmod object).

Typically you call this function for a variance model embedded in an earth model.

Usage

## S3 method for class 'varmod'
plot(x = stop("no 'x' argument"), which = 1:4,
  do.par = NULL, info=FALSE,
  cex = NULL, caption = NULL,
  line.col = 2, min.sd.col = line.col,
  trace = 0, ...)

Arguments

x

A varmod object. Typically this is embedded in a parent earth object, and so you invoke this function with plot(earth.mod$varmod). The varmod.method argument must have been specified when building the earth model.

which

Which plots to plot. Default is 1:4 meaning all. The term parent below refers to the earth model in which the varmod is embedded.
1) fitted vs parent fitted
2) fitted vs parent first predictor
3) residuals vs fitted
4) model selection graph (only when varmod.method="earth" or "x.earth").

do.par

Please see plotres

info

Plot some additional information, including lowess fits in the first two plots.

cex

Character expansion.

caption

Default is NULL, meaning automatically generate an overall caption.

line.col

Color of lines in the plots. Default is red.

min.sd.col

Color of the min.sd dotted horizontal line. Default is line.col. Use 0 to not plot this line.

trace,...

Similar to plotres

Note

The horizontal red dotted line in the first two plots shows the value of min.sd. See earth's varmod.clamp argument.

See Also

Examples

data(ozone1)

set.seed(1) # optional, for cross validation reproducibility

# note: should really use ncross=30 below but for a quick demo we don't

earth.mod <- earth(O3~temp, data=ozone1, nfold=10, ncross=3, varmod.method="lm")

plot(earth.mod$varmod) # plot the embedded variance model (this calls plot.varmod)

earth

Multivariate Adaptive Regression Splines

v5.3.0
GPL-3
Authors
Stephen Milborrow. Derived from mda:mars by Trevor Hastie and Rob Tibshirani. Uses Alan Miller's Fortran utilities with Thomas Lumley's leaps wrapper.
Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.