<>
Oh, great, but I will stick to Stata:
*************
sysuse auto, clear
qui reg pr we f rep tr tu
qui sum pr if e(sample)
sca sd=r(sd)
qui tabstat we f rep tr tu if e(sample), statistics( sd ) columns(variables)
save
mata
sds=st_matrix("r(StatTotal)")'
mata stata qui reg pr we f rep tr tu
bs=st_matrix("e(b)")[1..5]'
beta=bs:*sds:/st_numscalar("sd")
beta
end
*compare to beta option
reg pr we f rep tr tu, beta noheader
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Clive Nicholas
Gesendet: Mittwoch, 4. März 2009 10:56
An: [email protected]
Betreff: Re: st: can I get standardized coefficients by standardize
variables first?
Martin Weiss replied:
> Cheers, how do you calculate them then? I asked a couple of hours ago
about
> a way to get my hands on those beta coefficients w/o actually -egen,
> std()-ing the variables...
We are talking about beta coefficients, aren't we? As I remember it,
you calculate them by multiplying each regression coefficient by the
product of dividing its standard error by the standard error of the
dependent variable. That takes up three columns in your spreadsheet of
choice, and you do the sums in the fourth column.
--
Clive Nicholas
[Please DO NOT mail me personally here, but at
<[email protected]>. Please respond to contributions I make in
a list thread here. Thanks!]
"My colleagues in the social sciences talk a great deal about
methodology. I prefer to call it style." -- Freeman J. Dyson.
*
* 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/
*
* 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/
