Previously I have been using GLIMMIX with the LOGIT link to look at the effect of covariates and time on a disease diagnosis (0,1). Subject outcomes were recorded at 4 time points. The results looked reasonable. Most recently, I recoded the outcome so that if a subject had the disease at any time point they would also have the disease at later time points. The output looks terrible- the estimates are outrageously large. Could this be due to the correlations between timepoints? -G
... View more