st: gllamm

[w.mueller@uvt.nl]

Hi,

Could someone please tell me what the exact econometric model for the
following two gllamm estimations commands is?

1.
gllamm var1 var2, i(person group) family(binomial) link(probit)

Here, "var1" is a binary variable, "person" is a subject identifier and
"group" is the group identifier to which a subject belongs.


2.
gllamm var3 var4, i(person group) family(gaussian) link(id)

Here var3 is a continuous variable and "person" and "group" are as in 1.
above.


According to my reading of the Skrondal/Rabe-Hesketh book, the model for
1 should be:

var1_{ijk}=β₀ + β₁*var2 + β₂*person_{ijk} + η_{jk}⁽²⁾ + η_{k}⁽³⁾ + ζ_{j} 
+ ε_{ij}

where person_{ijk} are dummy variables for subjects, η_{jk}⁽²⁾ is the
random intercept for subject j in group k, η_{k}⁽³⁾ is the random
intercept for group k, ζ_{j} is a time-constant error component which
varies between subjects and ε_{ij} is a transitory error component which
varies over occasions i and subjects j. The random intercepts are
assumed to be independently normally distributed. Is this correct? What
about the model for 2.?


Best, Wieland.


*
*   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/