It has always surprised me that Cohen's d > 0.80 is considered a large effect size irrespective of the length of an intervention or treatment. How is contextual interpretation done in, say, education? It makes quite a difference whether the intervention is ten minutes or a year, right?
Indeed, but also what the measurement instrument looks like, its length, scoring.., the sample, and many other characteristics of the set-up of an intervention. See for example http://www.leeds.ac.uk/educol/documents/00002182.htm for a discussion of some of these aspects in relation to effect sizes (e.g. "Care must be taken in comparing or aggregating effect sizes based on different outcomes, different operationalisations of the same outcome, different treatments, or levels of the same treatment, or measures derived from different populations"). On a side note, in most meta-analyses "duration/length of treatment/intervention" is taken into account as a moderating variable (among others).
- Badges
- Science topic
- Similar topics
- Education