Dear Allstaters Not sure if my question is that difficult or even interesting, but would welcome comments. Am working on a parallel trial where a patient initially met the inclusion criteria, consented and then was randomised to treatment. One month later they died, and subsequently found out that they were not eligble for inclusion. Should they be included or excluded in analyses? Any thoughts? The order of randomistion will have been disrupted - is that a big problem? best wishes Philip Sedgwick St. George's, University of London.. You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.