Predicting accrual in clinical trials with Bayesian posterior predictive distributions

Stat Med. 2008 Jun 15;27(13):2328-40. doi: 10.1002/sim.3128.


Investigators need good statistical tools for the initial planning and for the ongoing monitoring of clinical trials. In particular, they need to carefully consider the accrual rate-how rapidly patients are being recruited into the clinical trial. A slow accrual decreases the likelihood that the research will provide results at the end of the trial with sufficient precision (or power) to make meaningful scientific inferences. In this paper, we present a method for predicting accrual. Using a Bayesian framework we combine prior information with the information known up to a monitoring point to obtain a prediction. We provide posterior predictive distributions of the accrual. The approach is attractive since it accounts for both parameter and sampling distribution uncertainties. We illustrate the approach using actual accrual data and discuss practical points surrounding the accrual problem.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Algorithms
  • Bayes Theorem
  • Clinical Trials as Topic / methods*
  • Clinical Trials, Phase III as Topic / methods
  • Data Collection / methods
  • Dietary Supplements
  • Docosahexaenoic Acids / administration & dosage
  • Female
  • Humans
  • Models, Statistical*
  • Patient Selection
  • Pregnancy


  • Docosahexaenoic Acids