1

I know how to interpret residuals in a linear regression model. I am now working in a model that predicts a binary target combining numerical and categorical variables.

My residual plots is as follows:

enter image description here

If this were residual plots from a linear regression model I would be able to interpret them and notice that they are terrible. However I do not know if the same interpretation must be done when working with a logistic regression model.

Ruben
  • 121
  • 3
  • I think you will find the information you need in the linked thread. Please read it. If it isn't what you want / you still have a question afterwards, come back here & edit your question to state what you learned & what you still need to know. Then we can provide the information you need without just duplicating material elsewhere that already didn't help you. – gung - Reinstate Monica Dec 26 '16 at 18:02
  • Thanks a lot for the answer. I read a lot of cross-validated posts but didn't find this one. If one should not look at those plots, how can I diagnose the model? – Ruben Dec 26 '16 at 18:08
  • That's OK. Sometimes stuff is hard to find. What do you want to diagnose about the model? – gung - Reinstate Monica Dec 26 '16 at 18:15
  • I would like to asses the goodness of fit of the model. – Ruben Dec 26 '16 at 18:16
  • That's a little under-specified (because we need to determine what we mean by "the goodness of fit" in a logistic regression context), but it's a good question. (It is also a different question than this 1.) Most likely, what you want has already been covered on CV. Try reading through the results of [this search](http://stats.stackexchange.com/search?tab=votes&q=%5blogistic%5d%20goodness%20of%20fit%20is%3aquestion). You should learn a lot. Most likely you will learn what you need to know, but if not you should be in a position to ask what you need w/o duplicating existing threads. – gung - Reinstate Monica Dec 26 '16 at 18:24

0 Answers0