Hi Eva,
I can't replicate this result - in the simple example below the mean
SE is very close to the SD of the beta (.1009669 vs .1009727) despite
the relatively small sample size (N=100):
Arne
set seed 12345
capture program drop simreg
program simreg, rclass
version 9.2
drop _all
set obs 100
gen x = invnorm(uniform())
gen e = invnorm(uniform())
gen y = x + e
reg y x
return scalar b = _b[x]
return scalar se = _se[x]
end
qui simulate b=r(b) se=r(se), reps(5000): simreg
sum b se
On 31/08/2007, Eva Batistatou
<[email protected]> wrote:
> Hi everyone.
>
> A quick question:
>
> I run some simulations and after regression analysis on 5,000 simulated
> datasets,I calculate the mean slope b and mean standard error of b's.We know
> that the mean SE(b)=standard deviation(b1,...,b5000).However,when instead of
> reporting the mean SE,I calculate the SD of b's,I find different results.Is it
> possible that this has to do with how STATA calculates the standard errors??
>
> Thanks in advance!
>
>
>
>
>
> --
> Eva Batistatou
> PhD Student
> Biostatistics Group
> Division of Epidemiology and Health Sciences
> School of Medicine
> University of Manchester
> Tel: +44 (0) 161 275 5666
> *
> * 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/
