Cohen's d in single sample t test is computed in a very strange way, help me understand why.
In the newest version of JASP (0.14.1.0) I don't understand why Cohen's d is computed as the Sample Mean divided by the SD. It doesn't make sense to me how knowing that the sample mean is X standard deviations higher than zero would be useful information. As I understand Cohen's d, it should be the difference between the sample mean and the test value divided by the SD. Knowing that the mean difference (the effect tested by the t value) is X standard deviations is useful information. Can anyone help me understand why this version of JASP is computing Cohen's d this way?
Comments
Hi,
I move this discussion to the JASP subforum. Then you'll probably get a reply swifter ;)
Eduard
This is a recent change in JASP. We had our reasons but people got really confused, so we're changing it back. See our GitHub page for a discussion.
Cheers,
E.J.