The impact of selection bias on test decisions in randomized clinical trials

Abstract

Selection bias affects the evaluation of clinical trials, for example, by elevating type I error rate. We investigated the effect of selection bias on type I error rate considering permuted block randomization. We also considered stratified randomization in general and for the special case of multicenter clinical trials, where we incorporated preferences of the investigator in our approach. Finally, the effect of underrunning is modeled, that is, where the randomization list exceeds the actual number of patients taking part in the trial. For all situations, we illustrate and discuss the impact of selection bias on type I error rate.