How to Convert Cohen's d to NNT
Author Information
Author(s): Furukawa Toshi A., Leucht Stefan
Primary Institution: Kyoto University Graduate School of Medicine/School of Public Health, Kyoto, Japan; Technische Universität München, Klinikum rechts der Isar, Munich, Germany
Hypothesis
This paper aims to empirically examine and compare two methods for converting Cohen's d into the number needed to treat (NNT).
Conclusion
Furukawa's method allows more accurate prediction of NNTs from Cohen's d compared to Kraemer's method.
Supporting Evidence
- Furukawa's method showed a high degree of agreement with actual NNTs in 97% of instances.
- Kraemer's method only overlapped with actual NNTs in 56% of instances.
- The study analyzed data from 10 randomized controlled trials.
Takeaway
This study looks at how to turn a number that shows treatment effect (Cohen's d) into another number that tells how many people need to be treated for one to benefit (NNT). It finds one method works better than the other.
Methodology
Meta-analyses of individual patient data from 10 randomized controlled trials of second generation antipsychotics for schizophrenia were conducted.
Limitations
The study relies on the estimation of control event rates to predict NNTs accurately.
Participant Demographics
The mean age of participants was 36.6 years, with 2895 men and 1383 women.
Statistical Information
P-Value
p<0.01
Confidence Interval
95%CI: 0.55 to 0.95
Statistical Significance
p<0.01
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website