Greetings.
My study design is as below:
- between subjects: 3 groups
- within subjects: pre & post measurements (9 measurements each)
GPower computation details as below:
- type: a priori
- effect size, f = 0.25
- alpha error = 0.05
- power = 0.80
- number of groups = 3
- number of measurements = should it be 2, 9 or 18 ?
- corr among rep measures = how to get this value? is it based on previous studies (if yes, kindly guide how)?
- nonsphericity correction = should it be 1? how to determine this?
Kindly advise on the above to calculate the sample size eventually.
Thank you.
To determine and estimate the sample for repeated-measures ANOVA, the researcher needs to know the means and standard deviations of the outcome at the different observations. The absolute differences between these values and their respective variances will provide an evidence-based measure of effect size.
The suggested steps for calculating sample size for a repeated-measures ANOVA in G*Power are below:
1. Open the G*Power.
2. Under the Test family drop-down menu: select F tests.
3. Under the Statistical test drop-down menu: select ANOVA: Repeated measures: within factors.
4. Under the Type of power analysis drop-down menu: select A priori: Compute required sample size - given alpha, power, and effect size.
5. Select the Determine button.
6. Select the Direct marker to highlight the menu.
7. In the Partial eta-squared box: insert one of the following values:
A. (.01) if the researcher believes there will be a small treatment effect.
B. (.03) if the researcher believes there will be a moderate treatment effect.
C. (.05) if the researcher believes there will be a large treatment effect.
8. Select Calculate.
9. Select Calculate and transfer to main window.
10. Insert .80 into the Power (1-beta err prob) box, unless researcher would like to change the power according to the current empirical or clinical context.
11. For the Number of groups box: insert (1)
12. For the Number of measurements box: insert the number that you have (3)
13. Select Calculate.
Article How Many Participants Do We Have to Include in Properly Powe...
Be careful with using G*Power for the sample size calculation for this design! You need to take into account that the effect size is evaluated in terms of a "double dissociation effect". See the discussion in: https://stats.stackexchange.com/questions/535159/gpower-difference-in-sample-size-for-ancova-vs-repeated-measures-anova-in-clin/
- Badges
- Science topic
- Similar topics
- Correction