Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: eivreg and cluster


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: eivreg and cluster
Date   Thu, 21 Feb 2008 11:16:54 -0500

Allison McKie <AMcKie@mathematica-mpr.com> :
-evireg- allows -bootstrap- which allows clustering.  I have no idea
if the bootstrap is consistent in this case.

sysuse auto, clear
bs: eivreg price weight foreign mpg, r(weight .85 mpg .9)
g manuf=word(make,1)
bs, cl(manuf): eivreg price weight foreign mpg, r(weight .85 mpg .9)


On Thu, Feb 21, 2008 at 10:07 AM, Allison McKie
<AMcKie@mathematica-mpr.com> wrote:
> Dear Statalist,
>
>  The eivreg command does not allow a cluster option.  Does anyone know a
>  statistically valid way to simultaneously (1) estimate regression
>  coefficients that use reliability to account for measurement error as eivreg
>  does and (2) obtain standard errors that adjust for clustering?
>
>  Thanks in advance for any help you can provide.
>
>  Regards,
>  Allison
>
*
*   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/



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