We all care about effect sizes. Yet, traditional ways of evaluating them (P < 0.05 and generic benchmarks) are failing us. We propose two paths forward: setting better, contextualized benchmarks or — more radically — letting go of benchmarks altogether. Both paths point to adjusted expectations, more detailed reporting and slow science.
- Friedrich M. Götz
- Samuel D. Gosling
- Peter J. Rentfrow
