R help - Sep 2011 - Correlation of variables with repeated measures.

Hello
I have a dataframe  that looks like this:

        Date   Min Subj     VAR1      VAR2       VAR3
1  8/30/2011  5min    1 34.41042 126.08490 55.3548387
2  8/30/2011 10min    1 34.53030 133.81343 61.6000000
3  8/30/2011 15min    1 34.66297 118.38193 11.8000000
4  8/30/2011 20min    1 34.82770 110.77767  6.6000000
5  8/30/2011  5min    2 36.36994 116.24861 41.2258065
6  8/30/2011 10min    2 36.37420 101.16457 13.6000000
7  8/30/2011 15min    2 36.37453  92.26340  0.4000000
8  8/30/2011 20min    2 36.37697  87.73650  0.0000000
9  8/30/2011  5min    3 35.25667 146.90037 10.0645161
10 8/30/2011 10min    3 35.36654 139.49364  6.0000000
11 8/30/2011 15min    3 35.33833 135.75633  0.4000000
12 8/30/2011 20min    3 36.01337 127.83797  0.0000000
13 8/30/2011  5min    4 35.26742  84.78603  0.9677419
14 8/30/2011 10min    4 35.17913  91.27093  1.8000000
15 8/30/2011 15min    4 35.09825  92.03692 13.4000000
16 8/30/2011 20min    4 35.36823  88.73337  4.8000000

and so on for more days.

I would like to check the correlation and p of  variables VAR1 VAR2 VAR3.

if I use cor.test(tel$VAR1, tel$VAR2)
 the observations are considered independent, and Indeed I got df=14
I have seen that I can obtain a correlation for each block using this
script:
http://stackoverflow.com/questions/2336056/how-to-do-correlation-with-blocks-or-repeated-measures

 I was wandering what I should do for obtain a correlation that account for
all the blocks.

	[[alternative HTML version deleted]]

I guess that I have just to consider the means of each subject,
as indicated here.

http://www-users.york.ac.uk/~mb55/intro/corrsim.htm

Thanks


On Thu, Sep 22, 2011 at 9:16 PM, Heverkuhn Heverkuhn
<heverkuhn@gmail.com>wrote:
> Hello
> I have a dataframe  that looks like this:
>
>         Date   Min Subj     VAR1      VAR2       VAR3
> 1  8/30/2011  5min    1 34.41042 126.08490 55.3548387
> 2  8/30/2011 10min    1 34.53030 133.81343 61.6000000
> 3  8/30/2011 15min    1 34.66297 118.38193 11.8000000
> 4  8/30/2011 20min    1 34.82770 110.77767  6.6000000
> 5  8/30/2011  5min    2 36.36994 116.24861 41.2258065
> 6  8/30/2011 10min    2 36.37420 101.16457 13.6000000
> 7  8/30/2011 15min    2 36.37453  92.26340  0.4000000
> 8  8/30/2011 20min    2 36.37697  87.73650  0.0000000
> 9  8/30/2011  5min    3 35.25667 146.90037 10.0645161
> 10 8/30/2011 10min    3 35.36654 139.49364  6.0000000
> 11 8/30/2011 15min    3 35.33833 135.75633  0.4000000
> 12 8/30/2011 20min    3 36.01337 127.83797  0.0000000
> 13 8/30/2011  5min    4 35.26742  84.78603  0.9677419
> 14 8/30/2011 10min    4 35.17913  91.27093  1.8000000
> 15 8/30/2011 15min    4 35.09825  92.03692 13.4000000
> 16 8/30/2011 20min    4 35.36823  88.73337  4.8000000
>
> and so on for more days.
>
> I would like to check the correlation and p of  variables VAR1 VAR2 VAR3.
>
> if I use cor.test(tel$VAR1, tel$VAR2)
>  the observations are considered independent, and Indeed I got df=14
> I have seen that I can obtain a correlation for each block using this
> script:
>
>
http://stackoverflow.com/questions/2336056/how-to-do-correlation-with-blocks-or-repeated-measures
>
>  I was wandering what I should do for obtain a correlation that account for
> all the blocks.
>
>
	[[alternative HTML version deleted]]