st: re: xtmixed question

[David Airey <david.airey@Vanderbilt.Edu>]

> When I use a maximum likelihood mixed model with clusters that have  
> unequal sizes, are the fixed effects modeled in a way that reflects  
> this?
>
> So in a model like,
>
> xtmixed y treatment || group:
>
> where multiple groups are each assigned to one of two treatments,  
> but groups are different sizes, is this accounted for by these  
> types of models?
>
> So if I were to average the groups and use the summary statistics  
> in a linear regression model, I might weight the analysis by  
> cluster size, reducing influence of small clusters relative to  
> large clusters. If I use xtmixed directly, should I worry about this?
The estimation method does deal indirectly with unequal sample sizes  
I have been told: "larger groups impose larger influences on the  
likelihood function to be maximized..."
*
*   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/