Interim Design Modifications in Time-to-Event Studies

Irle, Sebastian; Schäfer, Helmut

doi:10.1080/01621459.2011.644141

Cited by 31 publications

(59 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When analysing follow-up data on subjects who have already contributed to a decision about treatment choice, there is a danger of type I error inflation 34 but the methods of Jenkins et al . 35 and Irle and Schäfer 36 can be used to avoid this problem.…”

Section: Discussionmentioning

confidence: 99%

Optimizing the data combination rule for seamless phase II/III clinical trials

Jennison

2014

Statistics in Medicine

View full text Add to dashboard Cite

We consider seamless phase II/III clinical trials that compare K treatments with a common control in phase II then test the most promising treatment against control in phase III. The final hypothesis test for the selected treatment can use data from both phases, subject to controlling the familywise type I error rate. We show that the choice of method for conducting the final hypothesis test has a substantial impact on the power to demonstrate that an effective treatment is superior to control. To understand these differences in power, we derive decision rules maximizing power for particular configurations of treatment effects. A rule with such an optimal frequentist property is found as the solution to a multivariate Bayes decision problem. The optimal rules that we derive depend on the assumed configuration of treatment means. However, we are able to identify two decision rules with robust efficiency: a rule using a weighted average of the phase II and phase III data on the selected treatment and control, and a closed testing procedure using an inverse normal combination rule and a Dunnett test for intersection hypotheses. For the first of these rules, we find the optimal division of a given total sample size between phases II and III. We also assess the value of using phase II data in the final analysis and find that for many plausible scenarios, between 50% and 70% of the phase II numbers on the selected treatment and control would need to be added to the phase III sample size in order to achieve the same increase in power.

show abstract

Section: Discussionmentioning

confidence: 99%

Optimizing the data combination rule for seamless phase II/III clinical trials

Jennison

2014

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…Schäfer and Müller (2001) and Irle and Schäfer (2014) extend the conditional error rate principle. Wassmer (2006) and Jahn-Eimermacher and Ingel (2009) consider the inverse normal and Desseaux and Porcher (2007) Fisher's combination test approach.…”

Section: Adaptive Designs With Survival Datamentioning

confidence: 99%

“…Suggestions have also been made to construct valid adaptive test statistics including as much information as possible and allowing interim decision making on all collected data for multi-arm and population enrichment designs (Friede et al 2011;Jenkins et al 2011;Mehta et al 2014;Irle and Schäfer 2014;Carreras et al 2015). We describe these very important applications of adaptive designs in more detail in Part III of this book.…”

Section: Restriction Of the Information Used For The Adaptationsmentioning

confidence: 99%

“…Recently, some proposals were made to overcome the problem that Type I error rate control cannot be guaranteed anymore with the naïve use of the closed adaptive test. Essentially, proposals are either based on a modification of the combination testing principle or the CRP approach (Jenkins et al 2011;Magirr et al 2014a;Mehta et al 2014;Irle and Schäfer 2014;Stallard et al 2014;Carreras et al 2015) or requiring additional assumptions regarding the joint distribution of the primary and the short-term endpoints (Di Scala and Glimm 2011;Stallard 2010). There is intensive ongoing research in this area.…”

Section: Other Endpointsmentioning

confidence: 99%

See 1 more Smart Citation

Group Sequential and Confirmatory Adaptive Designs in Clinical Trials

Wassmer¹,

Brannath²

2016

Springer Series in Pharmaceutical Statistics

131

172

View full text Add to dashboard Cite

“…An alternative analysis strategy of adaptive survival trials based on patient‐wise separation was proposed and followed in different directions by Jenkins et al. (), Irle and Schäfer (), and Magirr et al. ().…”

Section: The Adaptive Setting— General Aspectsmentioning

confidence: 99%

Adaptive Designs for the One-sample Log-rank Test

Schmidt¹,

Faldum²,

Kwiecien³

2017

Biometrics

View full text Add to dashboard Cite

Traditional designs in phase IIa cancer trials are single-arm designs with a binary outcome, for example, tumor response. In some settings, however, a time-to-event endpoint might appear more appropriate, particularly in the presence of loss to follow-up. Then the one-sample log-rank test might be the method of choice. It allows to compare the survival curve of the patients under treatment to a prespecified reference survival curve. The reference curve usually represents the expected survival under standard of the care. In this work, convergence of the one-sample log-rank statistic to Brownian motion is proven using Rebolledo's martingale central limit theorem while accounting for staggered entry times of the patients. On this basis, a confirmatory adaptive one-sample log-rank test is proposed where provision is made for data dependent sample size reassessment. The focus is to apply the inverse normal method. This is done in two different directions. The first strategy exploits the independent increments property of the one-sample log-rank statistic. The second strategy is based on the patient-wise separation principle. It is shown by simulation that the proposed adaptive test might help to rescue an underpowered trial and at the same time lowers the average sample number (ASN) under the null hypothesis as compared to a single-stage fixed sample design.

show abstract

Interim Design Modifications in Time-to-Event Studies

Cited by 31 publications

References 20 publications

Optimizing the data combination rule for seamless phase II/III clinical trials

Optimizing the data combination rule for seamless phase II/III clinical trials

Group Sequential and Confirmatory Adaptive Designs in Clinical Trials

Adaptive Designs for the One-sample Log-rank Test

Contact Info

Product

Resources

About