Ryan, Working from the statement "it will allow for the test between correlation matrices across different time points (using the COVTEST statement), it assumes that the measurements between time points are not correlated", I would think that adding the second random statement specifying the correlation structure between time points addresses the assumption.  And I agree that the COVTEST statement will become particularly complicated.  It is why I ran away and hid from it last week (and to catch a plane).  It looks like all you would need to do, though, is systematize the matrix in the COVTEST statement using the general option. Steve Denham ... View more

Hi Ryan, Take a look at the documentation regarding estimable functions and especially Type III estimable functions.  These marginal estimators are valid, but with this caveat.  The missing values need to be at least "missing at random".  My problem is always "How do I tell if the missing data is missing at random, missing completely at random, or systematically missing?"  You'll have to look at the processes that generated the data at hand. Regarding problems for convergence--missingness can lead to problems in this area, both in non-convergence or convergence to a local extremum rather than the global extremum.  It seems to be even more of a problem for binary endpoints for me, and I don't know why. The bottom line, in my opinion, is that in most cases the unbalanced situation is by far best handled by mixed model methodology. Steve Denham ... View more