st: Re: Problem with Anovalator

[Arti Rayit <arti.rayit@yahoo.com>]

I am using xtmixed to analyse a dataset which is both unbalanced and has missing 
values:

xtmixed sc c.et##jaw##bracket##sex##fmpa || pid:,

and subsequently anovalator, from ATS, to investigate the interactions, but it 
fails as follows:

. anovalator bracket jaw sex,main 3way

anovalator main-effect for bracket  
chi2(1) = 2.3637885   p-value = .12418029
no such variables
r(111);

. anovalator jaw, main
no such variables
r(111);

The error seems to be related to jaw which has 2 levels(1,2), bracket has 3 and 
sex 2.

If I run
margins jaw##bracket##sex##fmpa, post  asbalanced emptycells(reweight)
I can test jaw.
. testparm i.jaw
 ( 1)  1bn.jaw = 0
 ( 2)  2.jaw = 0
           chi2(  2) = 9290.22
         Prob > chi2 =    0.0000
. test 1.jaw = 2.jaw
 ( 1)  1bn.jaw - 2.jaw = 0
           chi2(  1) =   29.75
         Prob > chi2 =    0.0000

 I would be grateful if somebody could tell me what I am doing wrong with 
anovalator.

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/