This question already has an answer here:

I have two logit regression models with different AIC. I'm using R. my first model has significant variables and AIC 192.7436. And my second model has 1 non-significant variables but with smaller AIC 192.4468. Which model is the best?


marked as duplicate by mkt, kjetil b halvorsen, Peter Flom regression Jul 21 at 12:52

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

  • 1
    $\begingroup$ What are the differences between your models ? What is your objective ? $\endgroup$ – Alexandre Cazenave-Lacroutz Jul 20 at 10:11
  • 3
    $\begingroup$ It is not appropriate to do significance testing to select variables for a model. See this. Don't delete "insignificant" variables. Pre-specify the model. Much more detail in RMS. $\endgroup$ – Frank Harrell Jul 20 at 10:55