W 13: Switching Endpoints Based on an Interim Analysis
David R. Bristol
Statistical Consulting Services, Inc. United States
Based on the results of the interim analysis, it may be decided to switch the roles of the primary endpoint and one of the secondary endpoints for the final analysis at completion of the trial.
This is development of methodology to use a secondary endpoint from an interim analysis as the primary endpoint for the final analysis.
The level of the test at the conclusion of the trial must be adjusted to control the overall Type 1 error rate. The adjustment incorporates both the interim analysis and the change in the primary endpoint, and is determined from the correlation between the two variables and the sample sizes for the interim analysis and the final analysis. Thus the adjustment can also be useful for re-estimation of the sample size for the end of the study, if necessary.
A secondary endpoint may become the primary endpoint, as long as the decision is made by an unblinded committee and the level of the test is adjusted appropriately.