st: Interaction term in repeated measures ANOVA or mixed model

["Roberts, Matthew (BHH)" <Matthew.Roberts@easternhealth.org.au>]

I have Stata/IC 11.2 for Mac

In my dataset, I have a continuous variable logntbnp measured on ~240 individual patients (id) on two occasions (visit=1 and visit=2).

I wanted to test if the change over time in logntbnp between visit=1 and visit=2 was different between 3 groups of patients (modality=0, modality=1, modality=2).

With data in long format, I ran:

anova logntbnp modality / id|modality visit modality#visit, repeated(visit)

The p for modality#visit was significant and I concluded that the change in variable logntbnp over time (visit) was significantly different among 3 groups of patients (modality).  The visit term was also significant.

It has been suggested that this difference might be due to differences between groups, i.e. age, diabetes etc.

Is the command below the way to set up a model that looks at this interaction and adjusts for the effect of age in anova?

anova logntbnp modality / id|modality visit modality#visit c.age, repeated(visit)

Would I be better off using xtmixed to do this?  How would this work to test the interaction?

Dr Matthew Roberts




________________________________

THIS E-MAIL IS CONFIDENTIAL. If you have received this e-mail in error, please notify us by return e-mail and delete the document. If you are not the intended recipient you are hereby notified that any disclosure, copying, distribution or taking any action in reliance on the contents of this information is strictly prohibited and may be unlawful. Eastern Health is not liable for the proper and complete transmission of the information contained in this communication or of any delay in its receipt.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/