hello list,

I have a statistical problem i was hoping you can help me with.

i have a built several multiple logistic regression models for my
data, and presented them in the results section of the manuscript.
In a second review of the ms, one of the reviewers asked if
interactions were performed and if not, why.
Now, we did not consider at the time to even use interactions, and now
i'm baffled as to what to do - i will definitely not construct all the
models again with interaction in them, mainly because he didn't ask us
too.

Do you guys know of a good reason as to why it is not necessary in
every case to use interaction in a multiple logistic model?

Thanks,

Hilit

-- 
Hilit Finkler
PhD student
Zoology department
The George S. Wise Life sciences faculty
Tel Aviv University
Israel

Reply via email to