plot.cumres: Plot cumulative residuals from a 'cumres' object

In gof: Model-diagnostics based on cumulative residuals

Description

plot displays the observed cumulative residual process with realizations under the null. 95% prediction bands

Usage

  ## S3 method for class 'cumres'
 plot(x, idx = 1:length(x$variable),
    col = c("grey"), ci = TRUE, col.ci = "darkblue",
    col.alpha = 0.3, lty.ci = 0, level = 0.95,
    legend = c("type1", "type2", "none"), xlab, ylab,
    vs = TRUE, ylim = NULL, title, ...)

Arguments

x	Object produced by the function cumres.
idx	vector of numbers (or variable names) indicating which processes from the x to plot.
col	Color of the sample processes. By setting this parameter to "none" or NULL no realizations will be drawn. The number of realizations is determined by the cumres-object.
ci	Type of prediction bands to plot. Defaults to none. Set to TRUE to obtain simultaneous prediction bands under the null (pointwise can be obtained by setting to "pointwise").
col.ci	Color of prediction band.
col.alpha	Degree of transparency (0-1) of the prediction bands.
lty.ci	Line type of prediction band.
level	The required prediction level.
legend	Type of legend where "type1" gives p-values of GoF-tests and "type2" gives usual type of legends.
xlab	Optional label of x-axis
ylab	Optional label of y-axis
vs	Label of predictor
ylim	Range of y axis
title	Main title
...	Additional arguments passed to the plot-routine.

Author(s)

Klaus K. Holst <[e-mail]>

See Also

cumres

Examples

n <- 500; x <- abs(rnorm(n,sd=0.2))+0.01; y <- sqrt(x) + rnorm(n,sd=0.2)
l <- lm(y ~ x)
g <- cumres(l, R=500)
plot(g, idx=1, ci="sim", col=NULL, col.ci="purple", legend="type2")

Example output

Loading 'gof' version 0.9.1

gof documentation built on May 2, 2019, 5:52 p.m.