-
Notifications
You must be signed in to change notification settings - Fork 29
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Custom contrasts #35
Comments
I love Jasp, but I sometimes resort to using SuperANVOA in emulation in order to perform custom contrasts. For example, I have a 2 (direction) x 3 (task) ANOVA [(2: same, orthogonal), (3: central, covert, saccade)], and for theoretical reasons I want to perform two Helmert contrasts (comparing the 3 task) -- one for the "same" condition and another for the "orthogonal" condition -- but I am unable to do that as JASP only allows contrasts along a main effect. |
I have never heard of SuperANOVA, but the visual display of interaction contrasts as pie charts is actually a pretty nice idea. |
SuperAnova (and it's companion package, StatView), was an extremely easy to use stats package that was released in the early 1990s (Mac only, later Statview was ported to Windows). It was originally developed by Abacus Concepts. They were later bought by SAS and killed off. The nice thing about SuperAnova's contrast interface is that there is no hand coding for contrasts: double clicking on any of the cells (e.g. "sac, same") automatically adds it as a positive weight. If you double click on another cell, both weights automatically become 0.5, and so on. Negative weights take an additional step: selection the cell(s) and click the "Add Minus" button. |
@felixthoemmes |
A nice feature might be to able to code your own contrast. SPSS calls this the LMATRIX in ANOVA designs (or MMATRIX in repeated measures designs). In R there is a function called fit.contrast() in the gmodels package. This would allow estimation of an interaction contrast. Currently, only pre-build contrasts are possible.
Would also be highly interested in a Bayesian counterpart. Using the BayesFactor package it is easy to get credible intervals for interaction contrasts, but unsure how to get a Bayes Factor for one contrast of interest.
The text was updated successfully, but these errors were encountered: