Clive,
How about this:
*! Cribbed from Jeff Pitblado's -zval-
program clive_centered
syntax varlist(min=1) [aw fw] [, PREfix(string) ]
/* check options */
if `"`prefix'"'!="" {
confirm name `prefix'
}
else {
local prefix "clive_"
}
if "`weight'"!="" {
local weight [`weight'`exp']
}
foreach name of local varlist {
capture confirm new variable `prefix'`name'
if _rc {
di as error "no action taken for `name': " /*
*/ "`prefix'`name' already exists"
}
else {
qui summ `name' `weight'
gen `prefix'`name' = (`name'-r(mean))
label var `prefix'`name' "Demeaned `name'"
}
}
end
exit
The syntax would be -clive_centered price-trunk-
Hope this helps,
Scott
----- Original Message -----
From: Clive Nicholas <[email protected]>
Date: Wednesday, August 25, 2004 2:11 pm
Subject: st: Automatic mean-centering?
> All,
>
> I'm interested in re-running old models by mean-centering all my
> continuous variables for comparison, as well as obtaining meaningful
> intercept values. At the same time, I wish to include dummy variables
> which, for obvious reasons, would not be mean-centered.
>
> Now I know how to do this manually, as we all do:
>
> . gen splodge = spludge-100
>
> where 100 is the mean of SPLUDGE. But I'm interested to know if
> there's a
> quicker way, especially if I have a _lot_ of continuous variables to
> mean-centre.
>
> Having explored the help files for -xi- and Mitchell and Ender's -
> xi3-
> (which IS downloadable via SSC, unlike -renvars-!), neither routine
> automatically creates mean-centered variables. Searching -findit-
> _and_the archive turned up nothing and nothing relevant respectively.
>
> If anyone has any ideas, I'd be keen to hear them. Ta!
>
> CLIVE NICHOLAS |t: 0(044)191 222 5969
> Politics |e: [email protected]
> Newcastle University |http://www.ncl.ac.uk/geps
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
