[R] Friedman test in R

[chet83]

Dear R users,

I am new to R and looking into using a Friedman test in R with post-hoc
analysis for a time series datset in which I am looking at changes in
multiple features over three time points in a number of individuals.  As
well as detecting if there is an overall difference in features between the
three time points I want to determine which features change significantly
and between which time points.  I therefore need to perform a post-hoc test
such as the wilcoxon signed-rank test. 

I am having trouble formatting my data and performing the formula:
friedman.test (y~A|B)
I think that y should be the feature measurements, A should be the time
points and B the subject. 

The data look something like this..

	subject	timepoint	feature1	feature2	feature3	feature4 ..
	1	1	26	32	43	45 
	1	2	45	63	3	87
	1	3	23	22	4	94
	2	1	76	44	79	79
	2	2	56	56	8	76
	2	3	87	23	7	67 

etc 

My question is how I could read this table into R in a format that would
allow the above test to be performed?   Also is there any way I can perform
post-hoc wilcoxon signed rank tests to determine which features are
different and between which time points? 

Thanks very much in advance for any help you can offer! 
 




--
View this message in context: http://r.789695.n4.nabble.com/Friedman-test-in-R-tp4660441.html
Sent from the R help mailing list archive at Nabble.com.