Statalist The Stata Listserver


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

Re: st: jknife with xtreg using jkrweight


From   "Stas Kolenikov" <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: jknife with xtreg using jkrweight
Date   Mon, 26 Feb 2007 21:52:18 -0600

If you have the jackknife weights, then -cluster- is excessive. The
control for the design is already built into the jackknife weights.
Just get rid of it, and see if that works.

What's on your reading/reference list on the jackknife weights?

On 2/26/07, Leslie R Hinkson (lhinkson@Princeton.EDU)
<lhinkson@princeton.edu> wrote:
I'm trying to run a two-level model (students nested within schools) using xtreg.
The dataset comes with 62 jackknife weights and I was wondering whether I could
somehow use those. So rather than having a command that looked like this:

jknife "xtreg depvar var1 var2 var3, re i(studentid)" _b _se, cluster(schoolid)

I might have something that looks like this:

jkrweight(srwt*, multiplier(1))] vce(jackknife) mse jknife
"xtreg depvar var1 var2 var3, re i(studentid)" _b _se, cluster(schoolid)


Where srwt* indicates the jackknife weights 1-62 with multiplier(1) indicating
a jknife 2 (as opposed to the default 1).

I've tried it of course and I keep getting an error term about the use of "cluster"
but nothing else. What am I doing wrong?
--
Stas Kolenikov
http://stas.kolenikov.name
*
*   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