Thanks to help from Yulia, I ran this analysis on an imported imputed dataset in Stata:
mi estimate, cmdok: xtmixed IEStot Group##MQvsComgrps##PTSS_2Grps##time || subject:, variance
I then wanted to test whether the four-way interaction was significant, and tried
mi test Group#MQvsComgrps#PTSS_2Grps#time
This form had worked OK with -xtmixed- with a single dataset (I used mi extract 1 to obtain it). However, it did not work with -mi- :
Group#MQvsComgrps#PTSS_2Grps#time not found
r(111);
I found, however, that the full specification of the test did work OK with -mi- :
. mi test 2.Group#2.MQvsComgrps#1.PTSS_2Grps#2.time ///
> 2.Group#2.MQvsComgrps#1.PTSS_2Grps#3.time ///
> 2.Group#2.MQvsComgrps#1.PTSS_2Grps#4.time
note: assuming equal fractions of missing information
( 1) [IEStot]2.Group#2.MQvsComgrps#1.PTSS_2Grps#2.time = 0
( 2) [IEStot]2.Group#2.MQvsComgrps#1.PTSS_2Grps#3.time = 0
( 3) [IEStot]2.Group#2.MQvsComgrps#1.PTSS_2Grps#4.time = 0
F( 3,23565.0) = 0.33
Prob > F = 0.8035
(I checked that this answer was correct by verifying that it was the same as that obtained with -mim- and dummy codes produced by -desmat-.)
This sounds more like a comment than a question, but I suppose my question is whether it is an oversight that
mi test Group#MQvsComgrps#PTSS_2Grps#time
doesn't work.
The error message doesn't suggest that it might be a problem caused by the use of different base categories with different imputed datasets, as mentioned on p. 53 of the MI manual.
Anyway, there's a way of obtaining the desired result, so I'm happy!
Thanks
Alan
*
* 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/
