Logistic regression from scratch

Re:Logistic regression from scratch by vhhn on Friday June 26, 2020 @08:32AM (#23651239)

You don't want to demean your dependent (response) binary variable. So you almost always want to keep beta0 to control for any imbalance in your dependent var.

[ Parent | on HN ]

Re:Logistic regression from scratch by cuchoi on Friday June 26, 2020 @02:05PM (#23655024)

I meant demeaning the independent variables. My understanding is that the beta_0 will have the meaning the curiousgal attach it only if you demean your independent variables.

[ Parent | on HN ]

Re:Logistic regression from scratch by vhhn on Friday June 26, 2020 @02:32PM (#23655306)

I see. But I think after demeaning X, beta0 will just have a special meaning... log odds of the average case. Nothing more.

[ Parent | on HN ]