Displaying 5 results from an estimated 5 matches for "predplot".
2002 Mar 26
2
does function predplot still exist?
Venables and Ripley's MASS 3ed mentions a function predplot, used for
plotting results of lda and qda. But even with the library MASS loaded,
R (1.4.1) tells me predplot doesn't exist, and when I search the 1.4.1
documentation for predplot, it finds nothing. Does predplot still
exist somewhere, or has it been replaced by a new and improved version
wit...
1999 Nov 19
1
max.col
I am trying to run, in R -Windows95, the example in MASS2,
section 17.2. When I run predplot() on cush.lda I get
> predplot(cush.lda, "LDA")
Error: couldn't find function "max.col"
I get the plot OK, but within predict(), it balks on max.col
A more general question about using VR. Is there an easy way
to use library on VR in general or do I have to move each...
2013 Feb 20
1
Plotting Discriminants from qda
Dear R Help Members,
I am aware how to plot the LD1 vs LD2 from a lda in R, using the code:
plot(baseline.systat.hat$x, col=baseline.systat.hat$class,pch=as.numeric(baseline.systat.hat$class))
However, I need to use the quadratic discriminant function, qda due to data properties. Is there a way to obtain the same sort of plot for from a qda object (and the output of predict qda). I have not
2006 Feb 23
0
pls version 1.2-0
...ethod does (the
default is to predict `NA').
- fitted() and residuals() now return NA for observations with missing
values, if na.action is na.exclude.
- `ncomp' is now reduced when it is too large for the requested
cross-validation.
- Line plot parameter arguments have been added to predplotXy(), so
one can control the properties of the target line in predplot().
- MSEP(), RMSEP(), loadings(), loadingplot() and scoreplot() are now
generic.
See the file CHANGES in the sources for all changes.
--
Ron Wehrens and Bj??rn-Helge Mevik
_______________________________________________...
2006 Feb 23
0
pls version 1.2-0
...ethod does (the
default is to predict `NA').
- fitted() and residuals() now return NA for observations with missing
values, if na.action is na.exclude.
- `ncomp' is now reduced when it is too large for the requested
cross-validation.
- Line plot parameter arguments have been added to predplotXy(), so
one can control the properties of the target line in predplot().
- MSEP(), RMSEP(), loadings(), loadingplot() and scoreplot() are now
generic.
See the file CHANGES in the sources for all changes.
--
Ron Wehrens and Bj??rn-Helge Mevik
_______________________________________________...