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: Repeated measures anova help
From
Douglas Coulter <[email protected]>
To
statalist <[email protected]>
Subject
st: Repeated measures anova help
Date
Mon, 12 Sep 2011 17:26:22 -0400
Hi Statalist,
I'm having some trouble running a repeated measures ANOVA in Stata and
I'm hoping someone can tell me if I'm going about this right... or if
this is even the right command to be using.
I'm evaluating a reading program where 10 schools get the intervention
and 10 control schools. My data includes fall and spring scores on the
reading test. I want to figure out if the the pilots and controls are
significantly different from each other from fall to spring and then
the again controlling for covariates like ethnicity and language
status. For all both of these I also need the means for the pilots and
controls.
I reshaped the data to be long, following what is suggested here
(http://www.stata.com/support/faqs/stat/anova2.html).
So I basically have something like this:
student readingtest timetested pilot ethnicity language
1 90 1 1 1 1
1 98 2 1 1 1
2 68 1 1 2 0
2 89 2 1 2 0
3 89 1 1 2 0
3 78 2 1 2 0
4 56 1 0 1 0
4 89 2 0 1 0
5 90 1 0 3 0
5 98 2 0 3 0
6 78 1 0 2 1
6 88 2 0 2 1
So I can't seem to figure out the simple syntax for repeated measures
anova without any covariates... I've been doing this first:
anova readingtest student pilot timetested, repeated(timetested)
But this gives me an error:
could not determine between-subject error term; use bse() option
So I tried this because, well, I didn't know what else to do:
anova readingtest student time#pilot, repeated(time)
And the same error. What is the appropriate way to do this?
Douglas
*
* 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/