Statalist


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

st: Question on xtmixed


From   vipul bhatt <vbhatt_22@yahoo.co.in>
To   statalist@hsphsun2.harvard.edu
Subject   st: Question on xtmixed
Date   Wed, 10 Feb 2010 07:55:57 +0530 (IST)

Hi Stata Users,

I have a question on xtmixed command for estimated mixed effects linear models in stata. I have the following equation to estimate:

y_{ijt} = b X_{ijt} + Error_{ijt}

where i indexes family, j indexes individual and t indexes time.

Also, Error_{ijt} = a_i + a_{ij} + a_{ijt}

I assume that these three error components are orthogonal to each other.


Now when  I estimate this equation in Stata I am using the following command:

xtmixed y x || familyID: || personID: ||,reml var

My question is does this command gives me estimates of all three variance components? I am assuming that this command only gives me estimate of variance of a_i and a_{ij}. Am I right in this assumption? If yes, then how should I change the above command to get estimate of variance of the transitory component a_{ijt}? 

Thanks!

Vipul



      Your Mail works best with the New Yahoo Optimized IE8. Get it NOW! http://downloads.yahoo.com/in/internetexplorer/

*
*   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   |   What's new   |   Site index