Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Re: Margins and interactions
From
Arti Rayit <[email protected]>
To
[email protected]
Subject
st: Re: Margins and interactions
Date
Fri, 13 May 2011 12:15:02 +0100 (BST)
I have a longitudinal experiment with 3 factors, a (3 levels) b (2 levels) and c
(2 levels) . As there is missing data and the data is not collected at regular
time intervals I have used xtmixed to analyse the data:
xtmixed sc c.et##a##b##c II pid:, ml
margins a##b##c, post asbalanced emptycells(reweight)
I would like to test if the a#b and possibly other interactions are significant.
Is it acceptable to fit the model with and without the a#b interaction and
compare the results with lrtest? I ask this because I understand that the way
the factors are coded can cause some difficulties in the interpretation of
effects.
Thank you,
Arti
*
* 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/