Correlation analysis by Groups

Leonardo_C

Hello to everybody,

I have a problem. How can I do, in JASP, separated correlation analysis for different classes of objects? I tried to use the "condition on" option for partial correlation, but it accepts only numerical variables, not categorical.

I could add a filter to the data matrix, but I would affect all other analysis i have made. Is it possible to create a filter valid for one specific analysis only?

Thanks for assistance.

Leonardo_C

EJ

Hi Leonardo_C,

Yes, you don't want a partial correlation. As of yet, filters are not analysis-specific. I guess you could re-order the data set such that each column is the class of objects you are interested in, but it is suboptimal. Maybe a GitHub issue is a good idea (https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/)

Cheers,

E.J.