Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Error in 2008 post on survey covariances
From
Steven Samuels <[email protected]>
To
[email protected]
Subject
st: Error in 2008 post on survey covariances
Date
Tue, 21 Dec 2010 18:52:36 -0500
-
Marlous Tuithof found a mistake in a formula I posted in 2008 for
computing covariances for survey data (see:http://www.stata.com/statalist/archive/2008-10/msg00087.html).I
am posting corrected code below. For those who need survey
correlations, I recommend Nick Winter's -corr_svy-, available at SSC.
I informed the original poster and I apologize to anyone else who used
the code.
Steve
[email protected]
18 Cantine's Island
Saugerties NY 12477
USA
Voice: 845-246-0774
Fax: 206-202-4783
*******************************************************
* Get covariances for survey data
* CORRECTED 2010-12-20
*******************************************************
sysuse auto,clear
svyset _n [pweight=rep78]
gen wt1000=weight/1000 // avoid large values
local cvars mpg wt1000 trunk //variable list
svy: mean `cvars'
foreach w of varlist `cvars' {
foreach v of varlist `cvars' {
gen double c_`w'_`v' = (`w' - _b[`w'])*(`v' - _b[`v'])
}
}
svy: mean c_*
*****************CODE ENDS*************************
*
* 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/