Abstract
Early stopping of a clinical trial is well accepted when there is enough evidence
for a significant effect. However, during the course of a trial, there can be reasons
to consider early termination for “futility.” In epidemiologic studies, costly or
destructive laboratory tests or slow case accrual can make it desirable to stop a
study early for reasons of efficiency. Estimation of the conditional power (CP) is
proposed as a decision tool to stop a study early or to continue it. We consider the
disadvantages of this method. We propose (group) sequential continuation of the trial
or study as a less arbitrary strategy. We re-analyzed two data sets from the literature
to illustrate the advantages of a sequential approach. We conclude that (group) sequential
analyses have several advantages over CP. More studies should consider a sequential
design and analysis to enable early stopping when enough evidence has accumulated
to conclude a lack of the expected effect. Such a strategy can save valuable resources
for more promising hypotheses.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Journal of Clinical EpidemiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Practical problems in interim analyses, with particular regard to estimation.Control Clin Trials. 1989; 10: 209S-221S
- Termination of a clinical trial with no treatment group difference: the Lupus Nephritis Collaborative study.Control Clin Trials. 1992; 13: 62-79
- Stochastic curtailing and conditional power in matched case-control studies.Stat Med. 1994; 13: 663-670
- Group sequential methods with applications to clinical trials.Chapman & Hall/CRC, Boca Raton2000
- Two-stage experimental designs: early stopping with a negative result.Appl Stat. 1992; 41: 181-190
- A method for deciding early stopping of inconclusive case-control studies in settings where data are stratified.Stat Med. 1997; 16: 2327-2337
- Early stopping to accept H0 based on conditional power: approximations and comparisons.Biometrics. 1997; 53: 794-806
- ‘A method for deciding early stopping of inconclusive case-control studies in settings where data are stratified’ by Strömberg U.Stat Med. 1999; 18 ([letter]): 361-363
- The design and analysis of sequential clinical trials.2nd edition. John Wiley & Sons, Chichester1997
- PEST4: Operating manual.Reading University, Reading (UK)2000
- Sequential analysis of matched dichotomous data from prospective case-control studies.Stat Med. 2000; 19: 3449-3464
- Patterns of patient enrollment in randomized controlled trials.J Clin Epidemiol. 2001; 54: 877-883
- Stochastically curtailed tests in long-term clinical trials.Comm Statistics-Sequential Analysis. 1982; 1: 207-219
- The futility index: an approach to the cost-effective termination of randomized clinical trials.Am J Med. 1985; 78: 635-643
- Conditional power calculations for early acceptance of H0 embedded in sequential tests.Stat Med. 1997; 16: 465-477
- Comparison of one-sample two-sided sequential t-tests for application in epidemiological studies.Stat Med. 1996; 15: 2781-2795
- Some practical aspects of the interim monitoring of clinical trials.Stat Med. 1994; 13: 1401-1409
Article info
Identification
Copyright
© 2003 Elsevier Inc. Published by Elsevier Inc. All rights reserved.
