Predicting event times in clinical trials when treatment arm is masked

J. Mark Donovan, Michael R. Elliott, Daniel F. Heitjan

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Because power is primarily determined by the number of events in event-based clinical trials, the timing for interim or final analysis of data is often determined based on the accrual of events during the course of the study. Thus, it is of interest to predict early and accurately the time of a landmark interim or terminating event. Existing Bayesian methods may be used to predict the date of the landmark event, based on current enrollment, event, and loss to follow-up, if treatment arms are known. This work extends these methods to the case where the treatment arms are masked by using a parametric mixture model with a known mixture proportion. Posterior simulation using the mixture model is compared with methods assuming a single population. Comparison of the mixture model with the single-population approach shows that with few events, these approaches produce substantially different results and that these results converge as the prediction time is closer to the landmark event. Simulations show that the mixture model with diffuse priors can have better coverage probabilities for the prediction interval than the nonmixture models if a treatment effect is present.

Original languageEnglish (US)
Pages (from-to)343-356
Number of pages14
JournalJournal of Biopharmaceutical Statistics
Volume16
Issue number3
DOIs
StatePublished - May 1 2006

Fingerprint

Clinical Trials
Bayes Theorem
Mixture Model
Population
Landmarks
Predict
Prediction Interval
Coverage Probability
Bayesian Methods
Treatment Effects
Parametric Model
Date
Timing
Simulation
Proportion
Converge
Prediction

Keywords

  • Bayesian prediction
  • Clinical trials
  • Survival analysis

ASJC Scopus subject areas

  • Pharmacology (medical)
  • Pharmacology, Toxicology and Pharmaceutics(all)

Cite this

Predicting event times in clinical trials when treatment arm is masked. / Donovan, J. Mark; Elliott, Michael R.; Heitjan, Daniel F.

In: Journal of Biopharmaceutical Statistics, Vol. 16, No. 3, 01.05.2006, p. 343-356.

Research output: Contribution to journalArticle

@article{429d4dc3f0384cfaba5a75c13885d29a,
title = "Predicting event times in clinical trials when treatment arm is masked",
abstract = "Because power is primarily determined by the number of events in event-based clinical trials, the timing for interim or final analysis of data is often determined based on the accrual of events during the course of the study. Thus, it is of interest to predict early and accurately the time of a landmark interim or terminating event. Existing Bayesian methods may be used to predict the date of the landmark event, based on current enrollment, event, and loss to follow-up, if treatment arms are known. This work extends these methods to the case where the treatment arms are masked by using a parametric mixture model with a known mixture proportion. Posterior simulation using the mixture model is compared with methods assuming a single population. Comparison of the mixture model with the single-population approach shows that with few events, these approaches produce substantially different results and that these results converge as the prediction time is closer to the landmark event. Simulations show that the mixture model with diffuse priors can have better coverage probabilities for the prediction interval than the nonmixture models if a treatment effect is present.",
keywords = "Bayesian prediction, Clinical trials, Survival analysis",
author = "Donovan, {J. Mark} and Elliott, {Michael R.} and Heitjan, {Daniel F.}",
year = "2006",
month = "5",
day = "1",
doi = "10.1080/10543400600609445",
language = "English (US)",
volume = "16",
pages = "343--356",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Predicting event times in clinical trials when treatment arm is masked

AU - Donovan, J. Mark

AU - Elliott, Michael R.

AU - Heitjan, Daniel F.

PY - 2006/5/1

Y1 - 2006/5/1

N2 - Because power is primarily determined by the number of events in event-based clinical trials, the timing for interim or final analysis of data is often determined based on the accrual of events during the course of the study. Thus, it is of interest to predict early and accurately the time of a landmark interim or terminating event. Existing Bayesian methods may be used to predict the date of the landmark event, based on current enrollment, event, and loss to follow-up, if treatment arms are known. This work extends these methods to the case where the treatment arms are masked by using a parametric mixture model with a known mixture proportion. Posterior simulation using the mixture model is compared with methods assuming a single population. Comparison of the mixture model with the single-population approach shows that with few events, these approaches produce substantially different results and that these results converge as the prediction time is closer to the landmark event. Simulations show that the mixture model with diffuse priors can have better coverage probabilities for the prediction interval than the nonmixture models if a treatment effect is present.

AB - Because power is primarily determined by the number of events in event-based clinical trials, the timing for interim or final analysis of data is often determined based on the accrual of events during the course of the study. Thus, it is of interest to predict early and accurately the time of a landmark interim or terminating event. Existing Bayesian methods may be used to predict the date of the landmark event, based on current enrollment, event, and loss to follow-up, if treatment arms are known. This work extends these methods to the case where the treatment arms are masked by using a parametric mixture model with a known mixture proportion. Posterior simulation using the mixture model is compared with methods assuming a single population. Comparison of the mixture model with the single-population approach shows that with few events, these approaches produce substantially different results and that these results converge as the prediction time is closer to the landmark event. Simulations show that the mixture model with diffuse priors can have better coverage probabilities for the prediction interval than the nonmixture models if a treatment effect is present.

KW - Bayesian prediction

KW - Clinical trials

KW - Survival analysis

UR - http://www.scopus.com/inward/record.url?scp=33646231035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646231035&partnerID=8YFLogxK

U2 - 10.1080/10543400600609445

DO - 10.1080/10543400600609445

M3 - Article

C2 - 16724489

AN - SCOPUS:33646231035

VL - 16

SP - 343

EP - 356

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

IS - 3

ER -