2
$\begingroup$

Suppose I have 2 by 2 contingency table. I performed Pearson's chi-squared test for independence and the results are significant. Does that mean the odds ratio that I calculated based on the 2 by 2 table is also significantly different from 1? I would say not necessarily since they are based on different kind of statistical test even though there is overlap in hypothesis. Please advise.

$\endgroup$
  • $\begingroup$ Which test are you using to get a p-value for the odds ratio? $\endgroup$ – Glen_b Dec 24 '15 at 3:54
  • $\begingroup$ Hi @Glen_b, thanks for the comment. I am using Wald test based on Maximum likelihood estimate of ln(odds ratio). $\endgroup$ – tatami Dec 25 '15 at 5:46

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.