Two of today's trials found no benefit. The useful question about any negative trial is whether it rules out an effect worth having, or simply failed to find one.
Look at the confidence interval, not the P value. If the interval excludes the smallest benefit you would care about, the trial has given a real negative answer. If it is wide enough to include an important benefit, the trial was inconclusive and the question is still open.
- Look at the confidence interval of the primary outcome, not just the P value
- Decide in advance the smallest benefit that would change your practice
- Call a trial negative only if its interval excludes that benefit
- Check whether the comparator was good usual care, which makes improvement harder to show
Why it matters
It is the difference between "this does not work" and "we still do not know".
Read the rest in the app
You have read your two free briefings this month. The app carries all 27 specialties, every morning, free — and this finding is waiting in it.
Scan to keep reading on your phone. No account needed to start.
Tomorrow morning, before your first patient
One edition a day for top clinical updates, written by the desk, every claim tied to its paper. Six minutes.
Get the app — free