The double infinitive CI is the best way to handle NNT when the ARR includes the zero value. If clinicians have any difficulty understanding it, it is because we have done a good job in teaching them its interpretation. See the following example. The percentages of patients achieving cure in a RCT comparing drugs A and B were 41% (76/186) and 33% (66/186) for A and B respectively. The difference in response rates was 8% and the 95% confidence interval of the difference in response rates was - 2% to 20%. The NNT of A Vs B in this study was 14 (1/.08). That is for every 14 patients treated with A instead of B, one additional patient would be cured. The 95% confidence interval of the NNT is 6 to -44. This interval means that the NNT may be as low as 6 but may go beyond infinity and may even favor B. The NNT favoring B Vs A may be as low as 44 but may go beyond infinity. >But this is the rub. Doug Altman's article (referred to by Zhang) > shows how to do this, and shows how it leads to a doubly infinite CI > for the NNT when the CI for the ARR spans 0, i.e. when p>0.05. >I don't think most clinicians can cope with this (I'd love to > have more than anecdotal evidence to base this on, but I'm scared of > risking mailbox overflow if I ask for a straw poll of you guys out > there). I'm sure it's easier to give point and interval estimates > for the ARR - which will be asymmetrical or more nearly symmetrical > anyway - preferably expressed on a percent scale. For example, the > ARR might be +10%, with 95% CI from -5% to +25%. The NNT is then 10, > with CI from -infinity to -20 and from -4 to +infinity. I know > which looks simpler to me. %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%