"Number of measurements" is simply the number of levels in your within-subject factor/repeated measure.If there is no between-subjects factor, you would enter 1. So say your design contains a factor "gender", the number of groups would be 2 (for male and female). "Number of groups" is simply the number of levels in your between-subject factor.So the design with 2 within-subject factors in the original post is currently unsupported: The most complex design that is currently supported by the "ANOVA: repeated measures" option can have a maximum of one between-subject and one-within subject variable (i.e. It is possible using the "Generic F test" option, but this is considerably more complicated. They informed me that the current version of G*Power (3.1.9.2) cannot conveniently do power analyses for repeated measures designs with more than one within-subject or between-subject factor. I had the same question, so I sent an e-mail to the G*Power team.
The problem is that if the correlations are high, the power analysis might be very, very conservative. If you estimate power as if the measures were independent, you know that your power analysis is conservative. The higher the correlations between your measures, the more power you have.
#Gpower mac how to
Second, I showed how to do this as a structural equation model, in a paper here: īoth of those approaches are a bit trickier to start with, but they are a lot more flexible.Ī third approach is to ignore the fact that it's repeated measures when estimating power. I prefer one of two other approaches which allow you to enter the data in matrix format.įirst, D'Amico, et al, showed how to do this in SPSS, using the (old) manova command: paper here: Power analysis for this type of design gets complicated rapidly, and it's not clear how to enter the appropriate parameters into GPower. (And then the other parameters depend upon which of the effects you want to base your power on). I suspect that you should therefore be entering two as the number of measures. However, GPower assumes that you want to do 1 test with 3 df, which you don't, you want to do 3 tests, with 1 df (2 main effects, 1 interaction).
So when you have a 2x2 repeated measures design, you have four measures. The groups are when you have a between case predictor - for example gender or experimental group. GPower is assuming you have your data set up so that a row is a case (often a person), and a column is a measure.įor example, if we measured Y on three occasions, we'd have Y1, Y2, Y3, and we'd have three measures.
0 kommentar(er)
