Dear All,
When reading a paper that gives crude Odds ratios (vs. placebo) and 95%
confidence intervals for two drugs.
What conclusions can be drawn from the data regarding whether there is
significant evidence of a difference between treatments.
e.g
if drug A OR 3.2 95% CI (0.88 - 15)
Drug B OR 7.2 CI (2.8 - 20.5)
the confidence intervals overlap, can we state that there is no significant
difference between the two? or can I only say that there is significance
evidence of a difference if the CI do not overlap? If no, can I calculate
the treatment differences from these data and CI ?
Thanks
________________________________________________________________________
Get Your Private, Free E-mail from MSN Hotmail at http://www.hotmail.com
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|