American Journal of Epidemiology Advance Access originally published online on October 12, 2005
American Journal of Epidemiology 2005 162(10):1033-1035; doi:10.1093/aje/kwi319
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
American Journal of Epidemiology Copyright © 2005 by the Johns Hopkins Bloomberg School of Public Health All rights reserved; printed in U.S.A.
Letter to the Editor |
RE: "USE OF A BAYESIAN APPROACH TO DECIDE WHEN TO STOP A THERAPEUTIC TRIAL: THE CASE OF A CHEMOPROPHYLAXIS TRIAL IN HUMAN IMMUNODEFICIENCY VIRUS INFECTION"
1 Julius Center, Universitaire Medisch Centrum Utrecht, 3508 GA Utrecht, the Netherlands
2 Center for Biostatistics, Utrecht University, 3508 TC Utrecht, the Netherlands
P.A.H.vanNoord@UMCUtrecht.nl
| The first 10% of the full text of this article appears below. |
We read the article by Kpozèhuoen et al. (1
) in the March 15, 2005, issue of the Journal with interest. As a methodological exercise, their Bayesian simulations are an important contribution in exploring the impact of different priors on reducing the size of a clinical acquired immunodeficiency syndrome trial. To compare the claimed efficiency gained by means of this Bayesian approach with an alternative method (2
, 3
), we performed a sequential statistical analysis