I am working with a binary logistic regression in SPSS and my current issue is that my baseline model is not significant (0.440) (Block 0 "Variables in the Equation), my Omnibus-test however is and the Chi-squared value is pretty high (171.162 for 15 df). When I include my independent variables I get some pretty good results that are significant and have interesting odds-ratios for my analysis (Block 1).

Does the non-significant value of my baseline model mean that I can't make any significant implications for the analysis, or can I disregard the insignificance in the baseline model? Is there any way to make it significant?

It's a social science research project with 988 respondents.


No, it doesn't mean that. The model with the intercept is usually uninteresting and whether the intercept is significant isn't important. I don't think there's a sensible way of making the intercept significant, but there's no reason to do so.

So, you can add independent variables.


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.