On 10/01/2011 22.03, Rod Jackson wrote: > Hi -- The interpretation of whether a finding is likely to clinically > significant or not, is one of key arguments for using CIs rather than > p-values. I don't think that CIs tell us more than P about clinical significance (in fact, they are closely correlated). What tell us about clinical effect are the outcome sizes (with or without intervention). P and CIs only tell us about how much we can trust the estimated effect size, cheers Piersante Sestini