As far as I know, variables with p>0.05 are non-significant for the regression model.

I found similar questions here about p-value like: What is the meaning of p values and t values in statistical tests?

and this one Interpreting non-significant regression coefficients

But those don't answer my main question which is: can I exclude the variables with p>0.05 and run the model again until I get only significant variables?

  • 2
    $\begingroup$ Sure you can. But the result is rarely worth the effort and often is meaningless. See our higher-voted threads on variable selection and model building. $\endgroup$ – whuber Feb 17 at 17:27
  • 2
    $\begingroup$ In line with whuber, the question whether you can and the question whether it's any good are quite different. ;-) $\endgroup$ – Lewian Oct 31 at 11:00
  • $\begingroup$ I see! Thanks whuber and Lewian So, although having non-significant variables, a model can be considered acceptable to define a specific case. It's a bit contra intuitive because it will increase the R^2, leadin Is that correct? Perhaps I need to create another question for this. $\endgroup$ – Hrpereira Nov 2 at 15:09

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.