Re: st: bootstrap _b VS bootstrap _se

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Wed, 21/7/10, Sirak wrote:
> But what if the coefficients which I found them significant
> ( with high t-values) in SUREG are not more significant in
> bootstrap _b, reps(1000). Isnt it this means the orginal
> findings dont replicate?? 

No, these are two different ways of estimating the standard 
errors. There exist (often conflicting) arguments you can use
to choose one method over the other, but if you find that the 
method matters, then I would just conclude that we don't know 
whether that statistic is significant or not. Some people use 
the term "on the boundary of significance".

Remember that the standard error, and thus the p-values and 
confidence intervals, are also just estimates, and thus are
themselves also uncertain. So, it should not come as a 
surprise that there exists a grey area where we don't know
whether a statistic is significant or not. Normally we don't
estimate the uncertainty in our standard errors, so we don't
notice it. We only tend to find this grey area when we 
compare different methods of estimating the standard errors,
as you found out.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------



      

*
*   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/