Statalist


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

Re: st: permute xtmixed


From   "Anders Alexandersson" <andersalex@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: permute xtmixed
Date   Mon, 22 Oct 2007 12:06:16 -0400

Here are a few suggestions:
Assert that the model converged each time, e.g., by adding something
like -assert e(converged)==1- as a command after -xtmixed-. -assert-
is your friend. Add the permute option seed(#) or -set seed #- before
calling -permute-, for replication purposes. Run again and examine the
output. If you need more detailed info, -set trace on-, run again and
examine why Stata complains. Does that help? Can you replicate the
problem using a Stata-provided dataset?

Anders Alexandersson
andersalex@gmail.com

Fotios Drenos <rmhafdr@ucl.ac.uk> wrote:

> I am trying to run a permutation tests on an xtmixed command and the
> I get a convergence error.
>
> The command I am using is:
>
> program test5, rclass
>         version 9
>         args dependent fac_gene fac_measurement
>         xi: xtmixed `dependent' i.`fac_gene' `fac_measurement'||sno:
> `fac_measurement', cov(unstruct)
>         testparm _I`fac_gene'*
>         return scalar pgene=r(p)
> end
>
>
> permute sqrtchol t=r(pgene), reps(100) noi : test5 sqrtchol gv242 visit
>
> Any suggestions of what goes wrong here?
*
*   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