I have obtained a likelihood ratio chi-squared test statistic and I don't know if it is significant or not. Do I:

  1. Compare my likelihood ratio chi-squared test statistic with the critical value in the chi-squared distribution table, as you do with a normal Pearson's chi-squared test statistic?

  2. Or do I just take the likelihood ratio chi-squared value (i.e., 0.821) and assume because it is greater than 0.05, it is insignificant?

  3. Or just read the P-value reported next to the likelihood ratio chi-squared?

  • $\begingroup$ "likelihood ratio", not "ratio likelihood". #3 is the answer. $\endgroup$ – Nick Cox Feb 28 '16 at 23:00
  • $\begingroup$ Thank you Nick! Sorry for writing it the wrong way round! $\endgroup$ – Pixie Feb 28 '16 at 23:03
  • $\begingroup$ See this video youtube.com/watch?v=HwD7ekD5l0g starting at time (1:00). The p-value is the area to the right of the test statistic. $\endgroup$ – Zachary Blumenfeld Feb 29 '16 at 0:48
  • $\begingroup$ Thank you for your help and YouTube link. One last question, when reporting the likelihood ratio chi-square test statistic, do we still use the symbol X2? Or do we write it as Likelihood Ratio X2= 0.035? I can't seem to find a specific symbol for the likelihood ratio chi-sq test statistic, and I do not want to give the impression I have done a Pearson's chi-sq test by just reporting the test statistic as X2= 0.035. $\endgroup$ – Pixie Feb 29 '16 at 14:04
  • $\begingroup$ I would report your sample size, degrees of freedom, chi square statistic and p-value. So long as you state that those results are from a likelihood ratio test there should be no issue with interpretation....I do not think there is a global standard (there may be some standards for specific academic journals or sub-feilds though) $\endgroup$ – Zachary Blumenfeld Mar 2 '16 at 3:35

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.