Stopping rules for long-term clinical trials based on two consecutive rejections of the null hypothesis

Mohamed Mubasher and Howard E. Rockette

Communications in Statistics - Theory and Methods, 2017, vol. 46, issue 3, 1342-1351

Abstract: A strategy for stopping long-term randomized clinical trials with time-to-event as a primary outcome measure has been considered using the criteria requiring multiple consecutive (or non consecutive) rejections at a specified α-level that controls against elevation of type I error. The procedure using two consecutive rejections is presented in this work along with the corresponding α-levels for the interim tests. The boundary cutoff values for these interim levels were determined based on an overall prespecified test size and were calculated using multidimensional integration and/or simulations. The reduction in the interim α-level values that is required to maintain the experiment-wise error rate is found to be modest. The power of the test is evaluated under various alternative accrual and hazard patterns. This procedure provides a more realistic stopping rule in large multi-center trials where it may be undesirable to terminate a trial unless a sustained effect has been demonstrated.

Date: 2017
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2015.1019142 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:46:y:2017:i:3:p:1342-1351

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2015.1019142

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().