stats (version 3.6.2)

# plot.ppr: Plot Ridge Functions for Projection Pursuit Regression Fit

## Description

Plot the ridge functions for a projection pursuit regression (ppr) fit.

## Usage

# S3 method for ppr
plot(x, ask, type = "o", cex = 1/2,
main = quote(bquote(
"term"[.(i)]*":" ~~ hat(beta[.(i)]) == .(bet.i))),
xlab = quote(bquote(bold(alpha)[.(i)]^T * bold(x))),
ylab = "", …)

## Arguments

x

an R object of class "ppr" as produced by a call to ppr.

the graphics parameter ask: see par for details. If set to TRUE will ask between the plot of each cross-section.

type

the type of line (see plot.default) to draw.

cex

plot symbol expansion factor (relative to par("cex")).

main, xlab, ylab

axis annotations, see also title. Can be an expression (depending on i and bet.i), as by default which will be eval()uated.

further graphical parameters, passed to plot().

None

## Side Effects

A series of plots are drawn on the current graphical device, one for each term in the fit.

## Examples

Run this code
# NOT RUN {
require(graphics)

rock1 <- within(rock, { area1 <- area/10000; peri1 <- peri/10000 })
par(mfrow = c(3,2)) # maybe: , pty = "s"
rock.ppr <- ppr(log(perm) ~ area1 + peri1 + shape,
data = rock1, nterms = 2, max.terms = 5)
plot(rock.ppr, main = "ppr(log(perm)~ ., nterms=2, max.terms=5)")
plot(update(rock.ppr, bass = 5), main = "update(..., bass = 5)")
plot(update(rock.ppr, sm.method = "gcv", gcvpen = 2),
main = "update(..., sm.method=\"gcv\", gcvpen=2)")
# }

Run the code above in your browser using DataCamp Workspace