Properties of a nonparametric test for early comparison of treatments in clinical trials in the presence of surrogate endpoints

A nonparametric test is derived for comparing treatments with respect to th e final endpoint in clinical trials in which the final endpoint has been ob served for a random subset of patients, but results are available for a sur rogate endpoint for a larger sample of patients. The test is an adaptation of the Wilcoxon-Mann-Whitney two-sample test, with an adjustment that invol ves a comparison of the ranks of the surrogate endpoints between patients w ith and without final endpoints. The validity of the test depends on the as sumption that the patients with final endpoints represent a random sample o f the patients registered in the study. This assumption is viable in trials in which the final endpoint is evaluated at a "landmark" timepoint in the patients' natural history. A small sample simulation study demonstrates tha t the test has a size that is close to the nominal value for all configurat ions evaluated. When compared with the conventional test based only on the final endpoints, the new test delivers substantial increases in power only when the surrogate endpoint is highly correlated with the true endpoint. Ou r research indicates that, in the absence of modeling assumptions, auxiliar y information derived from surrogate endpoints can provide significant addi tional information only under special circumstances.