st: re: Repeated measures ANOVA

[David Airey <david.airey@Vanderbilt.Edu>]

> Dear statalisters
> I have a problem, maybe a simple problem for the majority of you  
> but complex for me.
> I?m studyng the effects of a kind of ocular surgery. I have a  
> dataset with 5 measurements (CH0-CH5) and two surgical techniques.  
> The 5 measurements are made in the same patients, so are repeated  
> measures.
> I put the data in long format and now i have a dataset with the  
> variables subject(id number), ch(variable that holds the  
> measurements), chnum(variable 0-5 that tells if it was ch0 or  
> ch1.... to ch5) tcir(the suirgical technique a 0/1 variable).
> I want to know if are differences in the mean of ch from point 0  
> (the day before the surgery) to point 5 (4 weeks after the  
> surgery), and if these differences are related with the surgical  
> technique.
> I wrote
> anova subject tcir ch chnum, repeated(chnum)
> and receive the message "variable not in the model"
> If i drop tcir everything is ok.
> How can i fix this problem? What is wrong?
> I read the Stata manuals, but i don?t understand very well the  
> solution.
> Can you help me please?
> Thank you
> Antonio Botelho de Sousa
> Bombarral-Portugal

Usually, the dependent variable is named right after the anova  
command....you are not doing this in your example code.

-Dave
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/