Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: ssm with hierarchical data


From   David Souther <davidsoutheremail@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: ssm with hierarchical data
Date   Sun, 21 Mar 2010 12:52:26 -0500

Then I guess the question is how to use -gllamm- to run a multilevel
model while still accounting for endogenous switching.  I looked
through the gllamm docs, website, and help examples, but found nothing
about this so far.  Anyone with any experience setting up a model with
both switching and multiple levels ??



On Sat, Mar 20, 2010 at 3:29 PM, Stas Kolenikov <skolenik@gmail.com> wrote:
> -ssm- is only a wrapper for the (far) more powerful -gllamm-. You need
> to learn the latter... and you won't use -ssm- again :))
>
> On Sat, Mar 20, 2010 at 3:24 PM, David Souther
> <davidsoutheremail@gmail.com> wrote:
>> I've got data on students across campuses with variables measured at
>> both levels, and I would like to account for the different levels of
>> aggregation while using -ssm-.  Currently, I'm using -ssm- to account
>> for the switching for a certain student treatment (it's not selection
>> because I observe students whether they got the treatment or not), so
>> the model looks like:
>>
>> ssm count_truancies i_SES i_atrisk i_GPA  i_absences i_gender i_grade
>> c_teacherexperience c_diversity c_crime year1 year2,  ///
>> s(treatment =  i_SES i_atrisk i_GPA i_immigrant i_absences
>> c_teacherexperience  c_treatmentFUNDS ) q(16) family(poiss) link(log)
>> adapt
>>
>> Where the DV for the main equation is a count of the number of
>> truancies, the switch model is determined by the dichotomous DV
>> treatment, and there are several individual level vars (prefix of
>> "i_") and campus level vars (prefix of "c_").  I've got another level
>> of school district data that I'd like to add to this model at some
>> point in the future.
>>
>> Is there some way to model the different levels of data aggregation
>> (or some kind of hlm, xt, or clustering technique)??
>>
>> Thanks in advance,
>> David
>> *
>> *   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/
>>
>
>
>
> --
> 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/
>

*
*   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   |   Site index