Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

st: -xtmixed- Crossed effets & hierarchy

From   Hobst <>
Subject   st: -xtmixed- Crossed effets & hierarchy
Date   Thu, 2 Sep 2010 08:32:50 -0700 (PDT)

I have estimated the following crossed random effects model:

xtmixed y x1 x2 x3 || _all: R.model || quarter: mle

this already worked pretty good.

Now, the models are nested within brands, so i would like to add one more
level to the model.

Is this right like this:

xtmixed y x1 x2 x3 || brand: || _all: R.model || quarter:, mle ??

The thing that confuses me is the need of the _all, R.. I dont really see
what that is used for. I followed the method presented in

Multilevel and Longitudunal Modeling Using Stata, Rabe-Hesketh & Skrondal,
Chapter 8

Thanks in advance for any review


Tobias Friedli
Bachelor Student at the University of Zurich

View this message in context:
Sent from the Statalist mailing list archive at
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index