[R] help with panel.lda

Silvia Lomascolo slomascolo at zoo.ufl.edu
Mon Jun 18 11:10:39 CEST 2007


I work with Windows, R version 2.4.1

I am trying to plot the results of a discriminant analysis done using the
lda function in the MASS library. The discriminant. analysis goes like this:

data.tb<-read.table('C:\\Documents and
Settings\\silvia\\Desktop\\dicrim_test.txt', header=T) ## the actual made-up
test matrix is pasted below
train<-sample (1:36, 15)
table (data.tb$group[train])
data.lda<-lda(group~., data.tb, subset = train)
predict (data.lda, data.tb[-train,])$class

Then I want to obtain a plot by writing: 

>plot(data.lda, cex=0.7, 2, xlab='LD1', ylab='LD2')

but it's not working.  It says that it could not find the function panel. 
When I include panel=panel.lda, it tells me that the object 'panel.lda' was
not found.  All I get is an empty plot in the graphics window.  Was I
supposed to create an object called panel.lda? I cannot find in the help
what that object might be.

Any help would be appreciated.
 
TABLE USED:
   group var1 var2 var3
1      1    3   55    6
2      1    4   66    7
3      1    5   55    8
4      1    4   66    7
5      1    3   44    6
6      1    3   55    5
7      1    3   44    4
8      1    4   44    3
9      1    4   44    7
10     1    4   66    6
11     2    5   88    9
12     2    4   99    8
13     2    8   88    9
14     2    9   76    8
15     2    8   66    9
16     2    9   99   10
17     2   10  100    9
18     2    4   99    9
19     2    8   88    8
20     2    9   76    9
21     2    8   66   10
22     2    9   99    9
23     3    2   11   11
24     3    3   22    2
25     3    1   33    3
26     3    1   11    1
27     3    2   44    2
28     3    3   22    3
29     3    4   11    1
30     3    1   11    1
31     3    2   22    2
32     3    3   33    3
33     3    1   11    1
34     3    1   44    2
35     3    2   22    3
36     3    3   11    1

-- 
View this message in context: http://www.nabble.com/help-with-panel.lda-tf3939027.html#a11172049
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list