Non-parametric methods for comparing multiple treatment groups to a control group, based on incomplete non-decreasing repeated measurements.

In the comparison of two or more treatment groups to a control group, consider a study with non-decreasing repeated measurements of the same characteristic taken over a common set of time points for each subject. Based on the vector of possibly incomplete responses from each subject, this paper considers asymptotically distribution-free tests of the equality of the groups. I propose consistent point estimators of the overall treatment differences and I derive non-parametric simultaneous confidence regions for the treatment effects. An example using data from a bladder cancer study illustrates the proposed methods.