0
$\begingroup$

I have a model in which I suspect two variables to may be related. However, one is a binary/dichotomous variable, while the other is a continous variable. What approach should be used to check if my statement has any merit or not? The Point-Biserial Correlation test, or...?

$\endgroup$
1
$\begingroup$

Yes, point-biserial correlation is an option. You can also run a t-test and compare means between the two levels of your binary variable. These two approaches actually are algebraically identical (Ref).

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.