Statistical Methodology for Interim Analysis

6 Meta-analysis, Group Sequential Study Designs, and other topics 

if this analysis provided compelling evidence to terminate the trial, it would be terminated at this point. If compelhng evidence to terminate the trial was not obtained, the trial would proceed to the point where three-fifths of the total sample size had been recruited, at which point the third interim analysis would be conducted. If this analysis did not provide compelling evidence to terminate the trial, recruitment would continue to 800 participants, when the fourth interim analysis would take place. If this did not provide compelling evidence to terminate the trial, recruitment would continue to the full sample size of 1000 participants, when the fifth and final analysis would take place. Regardless of the outcome of this analysis, the trial would terminate at this point, since it was stated in the study protocol that 1000 participants were the maximum number that would be recruited. 

By its nature, therefore, the group sequential design involves the possibility of multiple comparisons. In this example it is possible that five analyses could be conducted on data collected in this clinical trial. As was introduced in Sect. 4.4.1, there is an inherent problem with multiple testing. As more tests are performed, it becomes increasingly likely that a type I error will occur, i.e., that a result will erroneously be declared as statistically significant. As also noted in that chapter, fortunately the problem can be addressed completely satisfactorily by taking appropriate statistical care. 

---