Hi,
I'm analysing a longitudinal clinical trial using the xtgee procedure in
Stata. I would be very grateful for pointers to material on specifying
the correlation strucutre in these models.
It's not clear to me how to think about choosing a correlation
structure, either on substantive grounds, that is subject matter
grounds, or being data driven, that is based on the actual data.
The application here is looking at changes in fitness over time in
pregnant women.
--
Anthony Staines, Lecturer in Epidemiology, Department of Public Health,
UCD, Earlsfort Terrace, Dublin2, Ireland.
E-mail :- [log in to unmask] Web :-http://astaines2.ucd.ie/
Work :- + 353 1 716 7345 Fax :- +353 1 716 7407
Home :- + 353 1 849 1089 Mobile :- +353 1 86 606 9713
|