Statalist


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

st: RE: Re: booststrapping with xtabond


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Re: booststrapping with xtabond
Date   Fri, 4 Sep 2009 17:16:40 +0100

What sample size is involved in 

xtabond pcm AD_CVD yr82-yr94 if all==1 &
year<1992, pre(imp, endog) pre(ks, endog) pre(t, endog) maxldep(5)
maxlags(5)

all 4592? 

Nick 
n.j.cox@durham.ac.uk 

Andrew.Clapson@statcan.gc.ca

I was trying to do something very similar a little while ago, and I got
the same error as you did. I don't think I ever figured out why the
-bootstrap- command didn't work for me, possibly the size of my dataset,
or perhaps because it was an unbalanced panel, or maybe it just doesn't
like -xtabond-, I'm not sure.

I ended up programming the bootstrap procedure manually, I think.  As I
recall though, I only wanted to use -bootstrap- for comparison purposes
- is there a specific reason you require it?

Laura Rovegno

> I'm trying to do boostrapping of standard erros in a xtabond
> estimation, and I the following error message:
>
> . bootstrap, reps(10): xtabond pcm AD_CVD yr82-yr94 if all==1 &
year<1992, pre(imp, endog) pre(ks, endog) pre(t, endog) maxldep(5) maxl
> ags(5)
(running xtabond on estimation sample)

Bootstrap replications (10)
----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5
xxxxxxxxxx
insufficient observations to compute bootstrap standard errors no
results will be saved r(2000);

> Do you know what the problem may be? I have a sample of 4596
> observations (12 years x 383 groups).
>
> It works if I do it with a simple ivreg in first difference/

*
*   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/



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