I have binomial data and I'm fitting a logistic regression using generalized linear models in python in the following way:

glm_binom = sm.GLM(data_endog, data_exog,family=sm.families.Binomial())
res = glm_binom.fit()

I get the following results

Generalized Linear Model Regression Results

output of GLM

I would like to check my understanding of the goodness-of-fit metrics:

  1. Deviance is the variance not explained by the model (the lower the better)
  2. The Pearson chi2 number is the difference between the deviance above and the deviance of a model with all coefficients except the constant equal to zero.
  3. The p-value associated with this chi2 number determines whether this model is a good fit

I'd like to confirm these because I wasn't able to find a good source online. Also, am surprised the pvalue is not reported in the output summary - is there an easy way to get it?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.