Statalist


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

Re: st: lincom - how are standard errors calculated?


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   stata list <statalist@hsphsun2.harvard.edu>
Subject   Re: st: lincom - how are standard errors calculated?
Date   Wed, 15 Oct 2008 11:47:07 +0100 (BST)

--- Aca wrote:
> I think you missed the minus sign in the very first output. So no
> probs at all with var(A-B) = -varA + varB.

No, the general rule is:
var(aX + bY) = a^2var(X) + b^2var(Y) + 2abcov(X,Y)

in this case a = 1 and b = -1, so

var(1X + -1Y) = 1^2var(X) + (-1)^2var(Y) + 2 1 -1 cov(X,Y) =
var(X) + var(Y) -2cov(X,Y)

-- 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