I am struggling on how to report a significant categorical x continuous interaction, which I found using a negative binomial regression. I have posted the output from STATA below.

So far, I have said something along the lines of, "there was a significant lang2 by emotdys3 interaction term at age 3 (B = *, p = *), post hoc analysis showed the moderation in the opposite direction to expected. See Figure * for a plot visualizing this effect".

Id like to improve this, and think there may be things to report that I haven't. Can anyone help?

lang2 = categorical, emotdys3 = continuous, sdq_conduct = outcome, continuous. gendercomp/oecd = covariates. enter image description here


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.