Anova simple effects - mean difference and Cohen’s d have opposite signs

General help and assistance with jamovi. Bug reports can be made at our issues page: https://github.com/jamovi/jamovi/issues . (If you're unsure feel free to discuss it here)
Post Reply
rose
Posts: 1
Joined: Tue May 02, 2023 12:52 pm

Anova simple effects - mean difference and Cohen’s d have opposite signs

Post by rose »

Hi all,
I’m hoping someone might help me understand something that appears inconsistent in some output. We’ve just run a 2X3 between groups factorial anova, and am looking at the simple effects to disentangle the interaction. For some of the comparisons, the unstandardised mean difference is negative, but the corresponding Cohen’d is positive. Shouldn’t the sign of these values be consistent? Is there something about the way Jamovi calculates Cohen’s d that can result in the opposite sign to the unstandardised difference?
Thanks 😊
FFB709D8-5F78-4ED3-8B6B-27DEA54B6A72.jpeg
FFB709D8-5F78-4ED3-8B6B-27DEA54B6A72.jpeg (180.83 KiB) Viewed 4181 times
Post Reply