-gllamm- follows the general Stata syntax:
command dependent_variable [explanatory_variables] [if] [in], [options]
In what you have written above, everything is mixed up: options come
up in different places, are not separated by a comma, etc. Besides if
you just say "It gives me an error" without providing the copy of the
output, others can only guess as to what's going on.
On 1/22/09, Rahsaan Maxwell <[email protected]> wrote:
> Hello-
>
> I want to use GLLAMM to run a multilevel mixed regression in which the
> dependent variable is an unobserved latent variable with four observed and
> continuous components. The individual and group-level covariates are all
> observed.
>
> Is it possible to do this? What is the appropriate code? I have tried the
> code below but obviously that does not work.
>
> I read in Psychometrika that it might be appropriate to use a three level model
> with a single random coefficient at level 3. However, I still don't understand
> how to specify the loadings on the DV because the eq command only seems to work
> on the random effects after the grouping variable?
>
> Any help is much appreciated.
>
> Thanks,
>
> -Rahsaan
>
>
> gen const = 1
> eq var1: const
> eq var2: trstprl trstlgl trstplc trstplt
> gllamm nrf(1) eq(var2) iv1 iv2 etc if firstgen==1 , i(country) nrf(1) eqs(var1)
> nip(20) adapt
>
>
> *
> * 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/
