Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: covariance


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: covariance
Date   Sat, 14 Feb 2009 08:49:49 +0000 (GMT)

--- On Fri, 13/2/09, Carlos Rodriguez wrote:
> Please, could anyone tell me what is the difference between
> the covariance command and the "correlation-,coefficients" 
> command in Stata10?

There is no difference: both the -covariance- and the 
-correlation- don't exist in Stata. What does exist is
the -correlate- command, which has the options 
-covariance- and -_coef-. Is this what you mean?

> I have read the help files but I am still unsure which to
> use if I want to show whether two regressors are highly
> collinear or not.

You definitely do not want to use the -_coef- option for 
this. So, your choice is between -correlate- and 
-correlate, covariance-. Both are measures of linear 
association between variables, the difference is that 
correlations are standardized and covariances are not. You
can find a more complete discussion in any introductory
statistics text.

--Maarten

-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index