lms.
plot.lms(lms.obj, ask=F, id.n=3, ...)
lms object.
TRUE,
plot.lms operates in interactive mode.
id.n
most extreme points. Set to
FALSE if no points
are to be identified.
Default: 3.
Standardized LMS Residuals vs Fitted Values
id.n most extreme
points, depending on the options chosen.
This function is a method for the generic function
for class lms.
It can be invoked by calling
for an object x of the appropriate class, or directly by calling
regardless of the class of the object.
When
ask=T, rather than produce each plot sequentially,
plot.lms
displays a menu listing all the plots that can be produced.
If the menu is not desired but a pause between plots is still wanted
one must set
par(ask=T)
before invoking this command with argument
ask=F.
The last plot - the Diagnostic plot -
summarizes the results obtained from
lmsreg
and
cov.mve.
The plot is only produced if the option
mve=T
has been set
when calling
lmsreg.
The diagnostic plot shows the standardized LMS residuals versus the
robust distances (based on MVE)
of the corresponding
x.
This plot allows the user to distinguish between regular
observations, vertical outliers, good leverage points, and bad leverage points.
lms.obj <- lmsreg(stack.x, stack.loss) plot(lms.obj, ask=T) # interactive version oldpar <- par(ask=T) plot(lms.obj) plot(lms.obj, id.n=10) par(oldpar) # reset ask par