Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: bootstrap with fixed effects


From   joachim jarreau <joachim.jarreau@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: bootstrap with fixed effects
Date   Mon, 3 Dec 2012 00:11:47 +0100

Hi,

I am running this:

bs b=(_b[leav]), reps(5) noisily saving(bsres, replace): reg lv leav
ldist contig comlang i.repyear i.partyear, ro

on a sample of 1250 obs.
stata runs the five regressions and obtains the coefficients, but displays

- collinearity in replicate sample is not the same as the full sample,
posting missing values -

after each regression except the first one, and

- insufficient observations to compute bootstrap standard errors -
- no results will be saved -

at the end.

ok so collinearity changes from one bootstrap sample to the other, so
that some fixed effects are dropped in some and kept in other samples.
 But I would just want to store the values of the coeff on the
variable leav. That is why I put the b=(_b[leav]) option. But despite
this option, it does not store this coefficient value, although it is
well defined.
Is there a way to do this? thank you in advance.

joachim

Université Paris-1 Panthéon-Sorbonne
106 boulevard de l'Hopital
75013 Paris
(00331) 44 07 82 42

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index