I would be grateful for some advice on the correct approach to analysing
this experiment. The data is a series of matched results for 2 treatments on
48 patients and the number of results for each patient can vary from 4 to 8.
The outcome is binary success or failure, and the results were determined at
two different time periods. I originally analysed each time period using
McNemar's test but this does not allow me to test the effect of time. As an
alternative I used cross-section time series (xtlogit in Stata) to
investigate the effect of time and treatment but this does not allow for the
matched nature of the data.
Is there anyway I can compare the McNemar's chi-squares or odds-ratios or is
there an alternative approach I can use.
Many thanks.
Audrey
_________________________________________________________________
It's fast, it's easy and it's free. Get MSN Messenger today!
http://www.msn.co.uk/messenger
|