CMStatistics 2016: Start Registration
View Submission - CMStatistics
B1755
Title: On the selection of a randomization procedure in clinical trials Authors:  Ralf-Dieter Hilgers - RWTH University Aachen (Germany) [presenting]
Abstract: In randomized clinical trials randomization is the most important design techniques to avoid bias. This statement is based on long run consideration and might fail in small clinical trials. Consequently, an investigation of the properties of randomization procedures with respect to the impact of bias on the study result is of interest. On the other hand, this investigation implies a comparison study of randomization procedure in the planning phase o a trial.In this talk, I will show the impact of selection bias on the study results i.e. the type 1 error probability. As a consequence a scientific argumentation to select a randomization procedure is enabled.