two-stage stopping rule
in a clinical trial comparing two treatments, a strategy in which results are examined after only a fraction of the planned number of participants in each group has completed the trial (usually either half or two thirds of the patients). At this point, the test statistic is computed and the trial stopped if the difference between treatment means is significant at the significance level set for this first stage. If not, the remaining participants in each group are studied, the test statistic is recomputed, and the means compared at a significance level set for the second stage. The significance levels for the two stages should be such that they equal the overall significance level for the trial, usually .05 or .01.