Interim analyses

This section contains the following:


Any analysis used to compare efficacy or safety issues between the treatment arms prior to formal completion of a trial is called an interim analysis.  All interim analyses should be carefully planned in advance and described in the protocol.  The optimal timing and frequency of analyses will vary between trials but it is generally six monthly or annually, or after a given number of outcome ‘events’.  In most cases, the interim analysis should be performed by the trial statistician only and no other members of the trial research group should have access to the results.  An independent Data Monitoring Committee should be set up to view the results.

The format of the interim analyses should be agreed in advance with the Data Monitoring Committee.  It will often follow the structure described in the Dummy Tables with the addition of further details on adverse or safety issues.  Statistical testing is usually only performed on the primary outcome(s), but again this is at the discretion of the Data Monitoring Committee.  You should consider adding the proposed structure of the interim analyses to the protocol as an Appendix.

Formal statistical stopping guidelines can be applied to interim analyses, but these are only one of a number of considerations that a Data Monitoring Committee to take into account.  Others include the balance of risk and benefit and the consistency with external evidence. Details of the statistical methods and assumed boundaries for stopping, if any, should be given in the protocol.

Back to top

Things to consider when writing a protocol

Back to top

Illustrative examples - WHO pre-eclampsia trial

An interim analysis is going to be suggested to the DSMC to be conducted after the completion of the first 4500 subjects. If the difference between the proportions of occurrence of pre-eclampsia in the two groups is significant in a two-sided test at the level alpha=0.01 then the trial will be stopped prematurely. The adjustment for repeated testing at the final analysis will then be negligible, leaving a significance level of practically alpha=0.05. (WHO Multicentre Randomized Trial of Calcium Supplementation for the Prevention of Pre-eclamsia - go to protocol)

Back to top

Illustrative examples - Magpie trial

Whilst recruitment to the Magpie Trial is ongoing, interim results will be supplied, in strict confidence, to the chair of the data monitoring committee as frequently as requested. Meetings of the committee will be arranged periodically as considered appropriate by the chair but at least annually. In the light of the interim data, and of any other evidence or advice they wish to seek, the data monitoring committee will inform the chair of the steering committee if, in their view: (i) there is proof beyond reasonable doubt that - either for all women or for any particular category of women
- treatment with magnesium sulphate is clearly indicated or contra-indicated, and there is a reasonable expectation that this new evidence would materially influence patient management, or (ii) it is evident that no clear outcome will be obtained. Proof beyond reasonable doubt may be taken as a difference of at least 3 standard deviations in at least one of the primary outcomes. This has the practical advantage that the exact number of interim analyses is not important.  (MAGPIE Trial - go to protocol)

Back to top

Additional resources

Trial Protocol Tool resource iconAnalysis and interpretation checklist

This checklist was developed by Dave Sackett, who prepared it for the forthcoming 3rd edition of Clinical Epidemiology; A Basic Science for Answering Questions about Health Care, to be published by Lippincott, Williams & Wilkins in 2004.

Back to top

Web resource iconICH Harmonised Tripartite Guideline: Statistical Principles for Clinical Trials

This document provides guidance for the design, conduct, analysis, and evaluation of clinical trials of an intervention in the context of its overall clinical development.

Back to top

Trial Protocol Tool resource iconDamocles report checklist (to follow)

Back to top

Further reading

(To come)

Back to top

This page was last updated 19th October 2004.