Displaying 2 results from an estimated 2 matches for "b8544".
Did you mean:
28544
2007 May 30
1
test to compare significant correlation increase
Hi!
I am calculating correlation between two variables:
1. X versus Y
2. X versus Y(with a 3 steps lag)
I would like to test if the correlation
increase/decrease from 1 to 2 is significant or not.
Is there any function in R to do this? any hints?
Thanks for help :)
David Ria?o
Center for Spatial Technologies and Remote Sensing (CSTARS)
University of California
250-N, The Barn
One Shields
2007 Jun 16
0
Fwd: How to set degrees of freedom in cor.test?
You could calculate the confidence interval of the correlation at
your desired df: http://davidmlane.com/hyperstat/B8544.html
The below code takes as arguments the observed correlation, N, and
alpha, calculates the confidence interval and checks whether this
includes 0.
cor.test2=function(r,n,a=.05){
phi=function(x){
log((1+x)/(1-x))/2
}
inv.phi=function(x){
(exp(2*x)-1)/(exp(2*x)+1)
}
r.prime=phi(r)...