This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
I have a workflow that makes a linear regression on 19 independent variables. :)
What I want to do is rank them using partial R squared. To do so right now I have to run 19 linear regressions with the individual variables to get an R squared for each.
When I used to do my statistical models in R I used the ppcor package to calculate a straightforward partial correlation (partial R squared).
Has someone else had this problem? Does anyone have a smart way to do this or an R-based alteryx macro to calculate the partial R squared?
Any advice is appreciated.
This capability isn't built directly into the Alteryx GUI. I would recommend you use the R Code Tool to take advantage of the ppcor package.
Do you have any idea how I can do this coming out of an Alteryx linear regression tool? :)
Can you share a quick example of how you do this currently with R?