I am estimating a multilevel model, where the response of the second equation is made up of four different variables. I am interested in the combined effect of the four (so separate estimates for each response will be an undesired solution).
Such a situation will dictate the estimate of a multivariate linear model.
Can a multivariate estimate be combined with a multilevel estimate? If so how? If that is not possible, what alternative solution(s) should be employed?
The data is cross sectional longitudinal
Thank you
Lilach Nachum
Professor, International Business
Baruch College, City University New York
55 Lexington Avenue, New York, NY 10010, USA
*
* 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/
