So I'm doing a thesis on compassion meditation and I'm confused about the power analysis. When I calculated it in G*power, "total sample size= 34", but it's for a 2x2 mixed ANOVA, so does that mean that I actually need 68 participants?
4
-
$\begingroup$ Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. $\endgroup$– Community BotCommented Sep 11 at 5:50
-
$\begingroup$ Sorry, I'm trying to understand how to interpret Gpower, when the software says I need a sample size of 34, does it mean I need a sample size of 34 across my two groups? Or 34 for each group? We're doing a study comparing breath meditation to compassion meditation (between-groups), these two groups are getting assessed before intervention and after intervention on self-report questionnaires (within-groups). So when the Gpower states that I need 34 participants, do I need 17 participants in breath group and 17 in compassion group or 34 participants for each of these groups? $\endgroup$– BreeCommented Sep 11 at 6:18
-
$\begingroup$ It would be better to edit the extra info to your original question. However, what is your effect size? And for which effect - between, within, or the interaction? What is the assumed correlation between repeated measures? $\endgroup$– SointuCommented Sep 11 at 8:16
-
$\begingroup$ N=34 refers to total sample size (17 per group). However, it seems you are using the Gpower defaults, which will usually give you too small sample size. See here. You should change the effect size metric from "Options" to "As in Cohen - 1988". With that, using medium effect size of f(V)=.25 I get total sample size of N=128, which corresponds toe.g. what WebPower gives $\endgroup$– SointuCommented Sep 11 at 9:06
Add a comment
|