Correction to “Bayesian Monitoring of Event Rates with Censored Data,” by D. A. Follmann and P. S. Albert; 55, 603–607, DOI: 10.1111/j.0006-341X.1999.00603.x June 1999
Article first published online: 25 JUN 2013
© 2013, The International Biometric Society
Volume 69, Issue 2, page 556, June 2013
How to Cite
- Issue published online: 25 JUN 2013
- Article first published online: 25 JUN 2013
We would like to thank Guochen Song for pointing out an error in Follmann & Albert 1999 who developed a Bayesian approach to the monitoring of discrete survival data. The basic formulation was to regard the discrete failure times as coming from a multinomial distribution, for which the conjugate prior is Dirichlet. With censoring, the posterior distribution is a mixture of Dirichlet distributions. Guochen Song realized that the mixing probabilities for the mixed posterior Dirichlet distribution are incorrect.
The theorem in Follmann & Albert (1999) incorrectly stated that the mixing probability for was proportional to
where if and
The correct mixing probabilities have
if and if .