Welcome to Kristoffer Magnusson's blog about


Articles with the Cohen's d tag

Expected overestimation of Cohen’s d under publication bias

In this post I will use the theoretical and empirical sampling distribution of Cohen’s d to show the expected overestimation due to selective publishing. I will look at the overestimation for various sample sizes when the population effect is 0, 0.2, 0.5 and 0.8. The conclusion is that you should be weary of effect sizes from small samples, and that the issue is rather with type M (magnitude) errors than type I errors. At least is clinical psychology the pervasive problem is overestimation of effects and not falsely rejecting null hypothesis.

Read more

Cognitive behavioral therapy outperformed psychodynamic therapy on all outcomes in a randomized controlled trail

The dodo bird might be extinct in the real world but in the world of psychotherapy research it refuses to die. However, a group of German researchers recently put forward an article were they had randomized patients to either a PDT or CBT condition and measured the relative proficiency of the two orientations, and they found that their results delivered a convincing blow to the dodo bird verdict.

Read more

Effect of sample size on the accuracy of Cohen's d estimates (95 % CI)

When talking about confidence intervals, Jacob Cohen famously said: “I suspect that the main reason they are not reported is that they are so embarrassingly large!” (Cohen, 1994). In this post I’ll take a look at the relationship between the 95 % CI for Cohen’s d and it’s corresponding sample size.

Read more