The choice of sample size: a mixed Bayesian / frequentist approach

Pezeshk, Hamid; Nematollahi, Nader; Maroufy, Vahed; Gittins, John
April 2009
Statistical Methods in Medical Research;Apr2009, Vol. 18 Issue 2, p183
Academic Journal
Sample size computations are largely based on frequentist or classical methods. In the Bayesian approach the prior information on the unknown parameters is taken into account. In this work we consider a fully Bayesian approach to the sample size determination problem which was introduced by Grundy et al. and developed by Lindley. This approach treats the problem as a decision problem and employs a utility function to find the optimal sample size of a trial. Furthermore, we assume that a regulatory authority, which is deciding on whether or not to grant a licence to a new treatment, uses a frequentist approach. We then find the optimal sample size for the trial by maximising the expected net benefit, which is the expected benefit of subsequent use of the new treatment minus the cost of the trial.


Related Articles

  • Application of the Bayesian Decision-making. Liu Jie-jing; ZHANG Shi-guang // International Proceedings of Economics Development & Research;2012, Vol. 49, p50 

    There are large numbers of factors of uncertainty in the presence of market environment, so that the decision-making of decision-makers have a degree of risk. It is a workable solution that increases the amount of information to increase the reliability of the decision-making. In this article,...

  • Everyday Problem Solving: Experience, Strategies, and Behavioral Intentions. Patrick, Julie Hicks; Strough, JoNell // Journal of Adult Development;Jan2004, Vol. 11 Issue 1, p9 

    Experience and strategic flexibility predict performance on solving hypothetical everyday problems, although their relation to real-world behavior is largely unknown (e.g., M. Diehl, S. L. Willis, & K. W. Schaie, 1995). Moreover, few studies have examined highly salient, rare-event problems such...

  • Combining Moments and Samples—A Bayesian Approach. Center, Julian L. // AIP Conference Proceedings;11/7/2008, Vol. 1073 Issue 1, p127 

    A simple example is used to illustrate how several different types of information can be combined by Bayesian methods. In particular, techniques for combining population moments with sampling data are examined.

  • Bayesian decoding of neural spike trains. Koyama, Shinsuke; Eden, Uri T.; Brown, Emery N.; Kass, Robert E. // Annals of the Institute of Statistical Mathematics;Mar2010, Vol. 62 Issue 1, p37 

    Perception, memory, learning, and decision making are processes carried out in the brain. The performance of such intelligent tasks is made possible by the communication of neurons through sequences of voltage pulses called spike trains. It is of great interest to have methods of extracting...

  • Bayesian Adaptive Exploration. Loredo, Thomas J. // AIP Conference Proceedings;2004, Vol. 707 Issue 1, p330 

    I describe a framework for adaptive scientific exploration based on iterating an Observation-Inference-Design cycle that allows adjustment of hypotheses and observing protocols in response to the results of observation on-the-fly, as data are gathered. The framework uses a unified Bayesian...

  • Using Bayes' Rule to Update an Event's Probabilities Based on the Outcomes of Partially Similar Events. Bordley, Robert F. // Decision Analysis;Jun2011, Vol. 8 Issue 2, p117 

    No abstract available.

  • Feedback and response mode in performing a Bayesian decision task. Martin, David W.; Gettys, Charles F.; Martin, D W; Gettys, G F // Journal of Applied Psychology;Oct69, Vol. 53 Issue 5, p413 

    In a complex decision-making situation Ss received data generated by one of three hypotheses according to specified conditional probabilities. The Ss inferred which hypothesis had generated the data or estimated the probability of each hypothesis given the data. Feedback was given after each...

  • A Probabilistic Model for Predicting Software Development Effort. Pendharkar, Parag C.; Subramanian, Girish H.; Rodger, James A. // IEEE Transactions on Software Engineering;Jul2005, Vol. 31 Issue 7, p615 

    Recently, Bayesian probabilistic models have been used for predicting software development effort. One of the reasons for the interest in the use of Bayesian probabilistic models, when compared to traditional point forecast estimation models, is that Bayesian models provide tools for risk...

  • Multi-period Emergency Supplies Distribution Model with Disaster Information Update. Ge Honglei; Liu Nan // Advances in Information Sciences & Service Sciences;Apr2013, Vol. 5 Issue 8, p454 

    Based on the evolutionary rules of emergency incidents and continuous observation and updated features of disaster information, the Bayesian sequential decision-making model of multi-period emergency supply distribution is built for solving the multi-relief point selection problem in the...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics