[R] stats/debugging question hotelling t-sq

From: <toby909_at_gmail.com>
Date: Sun, 16 Mar 2008 04:09:00 -0700


Hi

I spent hours looking over my formula. Somehow I cant find the reason why it gives me different answer.

help appreciated.

x = as.matrix(read.table("http://www.niehs.nih.gov/research/atniehs/core/microarrays/docs/heinloth.txt",1))
x = t(x)    #now rows are subjects, cols are genes
x = x[order(rownames(x)),]    #order by treatment group oxygen,
ultra-violet, gamma radiation
y = x[26:45,1:10]
x = x[2:25,1:10]
p = ncol(x); p

nx = nrow(x); nx
ny = nrow(y); ny
n = nx+ny; n

# (t(x)-colMeans(x)) %*% t(t(x)-colMeans(x))

T2 = nx*ny/n * t(colMeans(x)-colMeans(y)) %*% solve( ( (nx-1)*cov(x)+(ny-1)*cov(y) )/( n-2 ) ) %*% (colMeans(x)-colMeans(y)); T2

library(ICSNP)
HotellingsT2(y,x)

http://en.wikipedia.org/wiki/Hotelling's_T-square_distribution

http://finzi.psych.upenn.edu/R/Rhelp02a/archive/60962.html



R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Sun 16 Mar 2008 - 11:29:49 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Sun 16 Mar 2008 - 14:00:23 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive