Article Text


1 Using Futility Study Designs and Sample Size Calculations to Improve Early Laboratory Studies
  1. B Tilley
  1. Division of Biostatistics, University of Texas School of Public Health, Houston, TX, USA


Futility designs have been used in Phase II human studies in cancer research for over thirty years. More recently the same designs have been applied in Phase II human studies in neurology. There has been little, if any application of these designs to laboratory studies. For initial laboratory experiments the sample size is often chosen as an n of 5, increasing the n a few more depending on observed results. Futility studies provide a more rigorous approach to determining the initial sample size for an experiment. To apply a futility design, investigators must have some knowledge of historical control rates in similar experiments in their laboratory, and must be able to specify the magnitude of an effect that would make an experiment worthwhile to pursue further. Using a futility approach to plan an initial laboratory study could reduce the chance of missing important effects that should be carried forward into more comprehensive experiments, and could reduce the chance of carrying forward experiments that have little likelihood of success. This session will present the concept of futility studies, provide laboratory-based examples, and discuss sample size calculation. At the end of the session participants should understand the concept of futility, be able to use standard software for sample size calculation, and be able to plan their own studies using a futility approach.

Statistics from

Request permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.