To whom it may concern
I am using G*Power to calculate appropriate sample sizes. The design of my experiment is a three-factorial design (e.g., 3 × 3 × 3). How can I calculate it? My previous experiment was a two-factorial design (e.g., 3 × 4), and I used the way which is shown in the images. Thanks in advance.
Chen
Hello Chen,
Use of G*Power can give different answers for different effects within your model; if you're trying to determine a sample size for the overall study, you'd have to evaluate each effect, then go with the largest of the estimated sample sizes that were computed.
Unfortunately, you didn't explain the 3 x 3 x 3 design (are these three factors all between-subjects, all within-subjects/repeated measures, or a mix?), so it's hard to make concrete suggestions on the specific set-up for any effect.
Good luck with your work!
David Morse
Dear Dr Morse
Thanks for your reply and reminder. Both experiments are repeated measures designs.
Regards
Chen
I think that g power does not support more than one within-subject factor: https://stats.stackexchange.com/questions/59235/repeated-measures-within-factors-settings-for-gpower-power-calculation
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size