 |
 |
Hi Derek, There are many ways to create it but I think the simplest is this: EV1: intercept (a column full of 1) EV2: group (coded as +1/-1, and not 1/0) EV3: age EV4: sex EV5: age*sex EV6: age*group EV7: sex*group EV8: age*sex*group Testing positive and negative contrasts for each of these EVs will give, in order: (1) global mean, (2) main effect of group, (3) main effect of age, (4) main effect of sex, (5-7): 2-way interactions, and (8) 3-way interaction. Although not strictly necessary, it makes all better behaved if you mean-center group, age, and sex before entering them in the design and doing the multiplications. All the best, Anderson On Wed, 26 Sep 2018 at 21:26, Derek Andrews <[log in to unmask]> wrote: > Dear Experts, > > I would be very grateful to anyone who can confirm the models and > contrasts below are correct. Particularly the three way interaction. > > Thank you! > > Best, Derek > > ######################################################################## > > To unsubscribe from the FSL list, click the following link: > https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1 > ######################################################################## To unsubscribe from the FSL list, click the following link: https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1