I do not know why log-linear is non-sensitive margins and logistic regression is sensitive margins. Both are using odds ratios Can anyone give some explanation.

  • 2
    $\begingroup$ Could you please elaborate more what you mean when you say "is non-sensitive margin" $\endgroup$ – gunes Oct 27 '18 at 15:29
  • $\begingroup$ Log-linear models are defined by margins free. In a contingency table, margins cannot impact on the set of odds ratios $\endgroup$ – Ildefonso Marqués Oct 28 '18 at 8:16

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.