[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Help-gsl] Where oh where did the correlation cofficient go?
|
From: |
Brian Gough |
|
Subject: |
Re: [Help-gsl] Where oh where did the correlation cofficient go? |
|
Date: |
Wed, 23 May 2007 10:25:56 +0100 |
|
User-agent: |
Wanderlust/2.14.0 (Africa) Emacs/21.3 Mule/5.0 (SAKAKI) |
At Mon, 21 May 2007 23:11:15 -0700,
Jack Denman wrote:
> I discovered this great library, but in the linear regression code I
> cannot find a way to get the correlation coefficient "rho" or r that
> indicates the degree if fit. Am I missing something?
Hello,
We return the covariance matrix which gives more
information, you can calculate the correlation
coefficient from it as rho = c11/sqrt(c00*c11).
--
Brian Gough
Network Theory Ltd,
Publishing the GSL Manual - http://www.network-theory.co.uk/gsl/manual/