R help - Mar 2010 - PCA

Hello,

I am trying to complete a PCA on a set of standardized ring widths from 8
different sites (T10, T9, T8, T7, T6, T5, T3, and T2).
The following is a small portion of my data:

T10 T9 T8 T7 T6 T5 T3 T2 1.33738 0.92669 0.91146 0.98922 0.9308 0.88201
0.92287 0.91775 0.82181 1.05319 0.92908 0.97971 0.95165 0.98029 1.14048
0.77803 0.88294 0.96413 0.90893 0.87957 0.9961 0.74926 0.71394 0.70877
1.07549 1.13311 1.23536 1.19382 1.2362 1.07741 1.20334 0.8727 0.77737
0.99292 0.92703 1.02384 0.99831 1.1317 0.93672 1.07909 0.88933 1.15587
1.20885 0.8983 1.06476 0.81845 1.09017 0.72909 0.75347 0.95826 0.90922
0.73869 0.74846 0.70481 0.49826 0.91824 1.39082 1.1281 1.05147 0.95839
1.20648 1.24587 0.65045 1.23251 0.80977 0.89714 0.90042 0.9543 0.86217
1.20818 0.82725 0.7666 1.11092 1.10328 1.16464 1.00707 1.09575 1.04647
0.79045 0.47331 0.88753 1.04699 1.0854 0.91803 1.03622 0.80624 0.905 1.28271
0.91963 0.90121 0.89136 0.97408 1.0449 1.00572 0.7703 1.48373 1.31837
0.97733 1.04229 1.23096 1.14002 1.09911 0.77523 1.31543

This is what I have done in R:

rm(list=ls(all=TRUE))
PCA<-read.csv("PCAsites.csv", header=TRUE)
PCA
attach(PCA)
names(PCA)

###using correlation matrix#####

p1 <- princomp(PCA, cor = TRUE)
summary(p1)
loadings(p1)
plot(p1)
biplot(p1)
p1$scores
screeplot(p1, npcs=4, type="lines")

The problem is that the purpose of this analysis is to derive a new data
set, using the first component, that I can work with. In other words, I am
doing this to compress the data into one column of ring widths. How do I
derive a new data set?

Thanks in advance for the help.

Xan

	[[alternative HTML version deleted]]

On Wed, Mar 10, 2010 at 4:42 PM, Xanthe Walker <xanthe.walker at
gmail.com> wrote:
> Hello,
>
> I am trying to complete a PCA on a set of standardized ring widths from 8
> different sites (T10, T9, T8, T7, T6, T5, T3, and T2).
> The following is a small portion of my data:
>
> T10 T9 T8 T7 T6 T5 T3 T2 1.33738 0.92669 0.91146 0.98922 0.9308 0.88201
> 0.92287 0.91775 0.82181 1.05319 0.92908 0.97971 0.95165 0.98029 1.14048
> 0.77803 0.88294 0.96413 0.90893 0.87957 0.9961 0.74926 0.71394 0.70877
> 1.07549 1.13311 1.23536 1.19382 1.2362 1.07741 1.20334 0.8727 0.77737
> 0.99292 0.92703 1.02384 0.99831 1.1317 0.93672 1.07909 0.88933 1.15587
> 1.20885 0.8983 1.06476 0.81845 1.09017 0.72909 0.75347 0.95826 0.90922
> 0.73869 0.74846 0.70481 0.49826 0.91824 1.39082 1.1281 1.05147 0.95839
> 1.20648 1.24587 0.65045 1.23251 0.80977 0.89714 0.90042 0.9543 0.86217
> 1.20818 0.82725 0.7666 1.11092 1.10328 1.16464 1.00707 1.09575 1.04647
> 0.79045 0.47331 0.88753 1.04699 1.0854 0.91803 1.03622 0.80624 0.905
1.28271
> 0.91963 0.90121 0.89136 0.97408 1.0449 1.00572 0.7703 1.48373 1.31837
> 0.97733 1.04229 1.23096 1.14002 1.09911 0.77523 1.31543
>
> This is what I have done in R:
>
> rm(list=ls(all=TRUE))
> PCA<-read.csv("PCAsites.csv", header=TRUE)
> PCA
> attach(PCA)
> names(PCA)
>
> ###using correlation matrix#####
>
> p1 <- princomp(PCA, cor = TRUE)
> summary(p1)
> loadings(p1)
> plot(p1)
> biplot(p1)
> p1$scores
> screeplot(p1, npcs=4, type="lines")
>
> The problem is that the purpose of this analysis is to derive a new data
> set, using the first component, that I can work with. In other words, I am
> doing this to compress the data into one column of ring widths. How do I
> derive a new data set?
>
the output of p1$scores is what you want, isn't it?  Or just one column of
it?

desiredScores <- p1$scores[ , 1]

p



-- 
Paul E. Johnson
Professor, Political Science
1541 Lilac Lane, Room 504
University of Kansas