R help - Jul 2000 - MANOVA

Hi

I need to compare the performance of two sludge inertization methods. For that i
want make a manova Wilks test.

Description of the experiment:

After the calcination at different temperatures my calcinated sludge are
submeted to the lixiviation test. In my tables i show the concentration of the
some elements in the extract phase.

The results:

Method A (calcination at 1100 C)

Chromium	Nickel	Aluminum	Zinc
2.0	3.0	2.7	2.3
2.1	3.1	2.8	2.2
1.9	3.2	2.6	2.3
2.2	3.1	2.8	2.2

Method B (calcination at 1500 C)
 
Chromium	Nickel	Aluminum	Zinc
2.1	3.1	2.6	2.2
2.3	2.9	3.0	2.5
1.9	3.0	2.6	2.2
2.2	3.0	2.9	2.1
2.4	3.1	2.7	2.2
2.3	3.0	2.6	2.1
1.8	2.8	2.7	2.0


Assumptions:

lambda = |W|/(|W + B|)

W is the pooled cross product matrix
|W| is the determinant of W
B  is a matrix of pooled and weighted between-sample mean deviations
T the cross product matrix = W + B

Main Problem:

How i can compute lambda in R environment?

Thanks in advance

Have a nice day

Jorge

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

I tried to compute Wilks Lamdba with the following code.

cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc
> metA<-read.table('./methodA.txt', header=T)
> metB<-read.table('./methodB.txt', header=T)
> metAbar<-apply(metA,2,mean)
> metBbar<-apply(metB,2,mean)
> metAcentred<-t(t(metA)-metAbar) # column centred Xij-xibar
> metBcentred<-t(t(metB)-metBbar) # column centred 
> WA<-crossprod(metAcentred) # compute W matrix 
> WB<-crossprod(metBcentred) # compute W matrix 
> Wt <- WA + WB
> met <- rbind(metA, metB) # all data in the same matrix
> metbar<-apply(met, 2, mean) # global mean vector
> BA <- nrow(metA) * (metAbar - metbar) %*% (t(metAbar)-t(metbar)) #
compute B matrix
> BB <- nrow(metB) * (metBbar - metbar) %*% (t(metBbar)-t(metbar)) #
compute B matrix
> Bt <- BA + BB
> lamdba <- det(Wt) / det(Bt+Wt) # Wilks Lamdba
> lamdba
[1] 0.4541112
> Wt.Bt.prod <- t(Wt) %*% Bt
> pillar <- eigen(Wt.Bt.prod)  # eigen for the Pillai test
ccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc

Somebody can comment this code?

Jorge


...........................................
The data:
 
"Method A (Sludge calcinated at 1100 C)"

methodA.txt
............................................
 Chromium	Nickel	Aluminum	Zinc
 2.0	3.0	2.7	2.3
 2.1	3.1	2.8	2.2
 1.9	3.2	2.6	2.3
 2.2	3.1	2.8	2.2
 ..........................................

"Method B (Sludge calcinated at 1500 C)"

methodB.txt
............................................  
 Chromium	Nickel	Aluminum	Zinc
 2.1	3.1	2.6	2.2
 2.3	2.9	3.0	2.5
 1.9	3.0	2.6	2.2
 2.2	3.0	2.9	2.1
 2.4	3.1	2.7	2.2
 2.3	3.0	2.6	2.1
 1.8	2.8	2.7	2.0
 ...........................................

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._