EVALUATION OF MULTICENTER CLINICAL-TRIAL DATA USING ADAPTATIONS OF THE MOSTELLER-TUKEY PROCEDURE

Two procedures, based on proposals discussed by Mosteller and Tukey, a re described for obtaining a combined estimate of the difference betwe en two treatment means and its confidence interval from multicentre cl inical trial data. Both procedures provide estimates in the possible p resence of heteroscedasticity. The first procedure is designated the p rimary analysis for efficacy assessment. It omits treatment-by-centre interaction from the error term for treatment, unless there is substan tial evidence of qualitative interaction (Ciminera et al.) or other sp ecial circumstances. The second procedure is the primary analysis when ever there is substantial evidence of qualitative interaction, and can be used whenever there are other reasons to make an analysis allowing for interaction.