| plot.quickPredict {STAR} | R Documentation |
plot, lines, image, contour and persp methods for
quickPredict objects.
## S3 method for class 'quickPredict':
plot(x, y, xFct = function(x) x, style = c("band",
"simple"), ylim, meanCol = 2, meanWD = 2, bandCol = "grey50", xlab,
ylab, ...)
## S3 method for class 'quickPredict':
lines(x, what = c("mean", "upr", "lwr"),
xFct = function(x) x, ...)
## S3 method for class 'quickPredict':
image(x, main, xlab, ylab, ...)
## S3 method for class 'quickPredict':
contour(x, what = c("mean", "sd"), main, xlab, ylab, add,
...)
## S3 method for class 'quickPredict':
persp(x, what = c("mean", "sd"), main, xlab, ylab, zlab, ...)
x |
a quickPredict object. |
y |
Not used but required by the plot method definition. |
xFct |
a function applied to the xx component of argument
x which is itself a quickPredict object. Useful
to get a plot with the "native" scale of the variable. |
style |
a character string, either "band" or "simple". Controls the way
confidence intervals are displayed. If "band" is selected
they are shown as a ribbon. Their boundaries appear as
dashed lines otherwise. |
ylim |
see plot (default provided if missing). |
meanCol |
the color used to display the estimated mean of the term
(see argument col in plot). |
meanWD |
the width used to display the estimated mean of the term
(see argument lwd in plot). |
bandCol |
the color of the confidence interval ribbon when one is is drawn. |
xlab, ylab, zlab |
see plot and
persp (default provided if any is missing). |
main |
see image, contour and
persp (default provided if missing). |
what |
for lines.quickPredict, one of the following character strings: "mean", "upr", "lwr".
Controls the line drawn: the estimated mean, upper bound of
the 95% CI or lower bound. For contour.quickPredict and
persp.quickPredict, a character string specifying if the mean
or the sd contours or surface
should be drawn. |
add |
see contour. |
... |
additional arguments to plot, lines,
image, contour and persp. |
Nothing returned, these functions are used for their side effects: plots are generated or modified.
Christophe Pouzat christophe.pouzat@gmail.com
quickPredict,
plot,
lines
image,
contour,
persp,
plot.ssanova
## Not run: ## Follow up of ssanova example of gss data(nox) nox.fit <- ssanova(log10(nox)~comp*equi,data=nox) ## get prediction for the first term, comp comp.pred <- quickPredict(nox.fit) ## plot result with method plot for quickPredict objects plot(comp.pred) ## get prediction for the second term, equi using the binary version equi.pred <- nox.fit plot(equi.pred) ## get prediction for the interaction term, comp:equi comp.equi.pred <- nox.fit ## use image method image image(comp.equi.pred) ## use contour method contour(comp.equi.pred,col=2,lwd=2,labcex=1.5) contour(comp.equi.pred,what="sd",lty=3,labcex=1.2,add=TRUE) ## use persp method persp(comp.equi.pred,theta=-10,phi=20) ## End(Not run)