Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Treatreg in the Svy context: no test for rho?


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Treatreg in the Svy context: no test for rho?
Date   Thu, 19 Jan 2012 11:31:14 -0500

You'd have to get the estimates out of the (semi-technical) results
that are actually produced by -treatreg-. You'd have to figure out the
parameter names (type -matrix list e(b)- to find out), then construct
(Wald-type) tests for the specific parameter values in the metric in
which they were estimated. In all likelihood, it will boil down to
something like

test [athrho]_cons == 0

On Thu, Jan 19, 2012 at 9:28 AM,  <federico.biagi@unibocconi.it> wrote:
> Dear community
> I am using the treatreg command in the context of survey data, hence after declaing svyset and using the svy brr command. The estimation works fine (only ML, no two steps) but I do not get the printout of either the estimated value for rho (and sigma) nor the LR test on rho (i.e. rho statistically different from zero). This is fundamental to understand whether we should use treaterg in the first place. Any suggestion on how to get rho and test its significance?

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index