Suggestion for Logistic Regression

Everything related to development of the jamovi platform

by MAgojam » Wed Feb 14, 2018 10:19 pm

Hi, jamovi team,

I really appreciate everything you all are doing with the jamovi package, and thank you so much for everything you all have done so far.

I wanted to suggest, for the next jamovi updates, the possibility to calculating Tjur (pseudo) R-squared values for logistic regression models.
But Kvalseth (1985) argued that it’s actually preferable that R-squared not be based on a particular estimation method. In that way, it can legitimately be used to compare predictive power for models that generate their predictions using very different methods.

User avatar
Posts: 92
Joined: Thu Jun 08, 2017 2:33 pm
Location: Parma (Italy)

by Ravi » Thu Feb 15, 2018 6:35 pm

Hi Maurizio,

Thanks for you suggestion, I'll look into adding that. Could you also make a github issue some I will not forget about it? You can make a github issue over here: Thanks!

User avatar
Posts: 151
Joined: Sat Jan 28, 2017 11:18 am

Return to jamovi development