st: Re: RM ANOVA, was SPSS vs. Stata

["Joseph Coveney" <jcoveney@bigplanet.com>]

Robert Ploutz-Snyder wrote:

" Doesn't SPSS wrap GLM for its RM-ANOVA routines?"

Yes--but with repeated measures designs, SPSS (and SAS, Systat, and BMDP in the
old days) use listwise elimination.  Stata does not (is there an option in
Stata's anova, repeated() code to do so??)

" Can you post an example of what you are talking about, re listwise
elimination? I don't have SPSS."

[example omitted]

Of course, with a sample size this tiny, we wouldn't trust either analysis.  The
point is that the prevailing wisdom for fixed-factorial repeated measures ANOVA
is to use listwise elimination, and Stata doesn't do this.  (And you get the
same Stata results if you use the anova command without the repeated option but
instead define the error terms manually--a process that is itself painful enough
to avoid entirely if you have 2 or 3 factors, especially if more than 1 are
repeated.) 

I appreciate that it is possible to "manually" tell Stata to ignore listwise
those subjects who are missing any data... However this can get more complicated
when there is more than 1 repeated measures factor (example, drugs a b c,
measured pre and post).  And... exactly what is Stata's analysis "by default"
anyway?  I could not write that up as a standard repeated measures ANOVA because
it isn't that.  To me, a straightforward improvement to Stata's -anova- would be
to force it to ignore any subjects who are missing any repeated measures
observations.  That alone would be useful.  

--------------------------------------------------------------------------------

There isn't an option in -anova , repeated()- to use listwise elimination to my
knowledge.

I believe that Stata's analysis by default is fixed-effects panel-data 
analysis.  Compare the results between -anova- and -xtreg , fe- with your 
example to see this.

You can use -fill- and then -drop if missing()- in order to help simplify 
manual listwise elimination.

Joseph Coveney

P.S.  The example that you gave is probably not the best one to make your case.

Unbalanced repeated-measures factors result in problematic bias with 
repeated-measures ANOVA when one factor is nested under another (i.e., is 
considered a random effect and the analysis depends upon estimating its 
variance), such as 

-anova score group / patient|group time group*time, repeated(time)-.  

Although the groups don't need equal numbers of patients (the dataset can be 
unbalanced in that sense), patients with missing observations across time will
cause problems in estimating the patient variance component, which is needed
for testing group effects.  

For the example that you gave, I would want to keep all available data (Stata's
default) and would be peeved with SPSS's automatically deciding on my behalf 
to perform listwise elimination.


*
*   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/