1
$\begingroup$

I am currently working on my dissertation project where my data are essentially all dummies. From my dependent to my independent variables, everything is a dummy variable (0,1), at least for the preliminary model. The data are cross-sectional.

I was wondering what the best model to use would be. I have decided to do a simple regression followed by logit and probit. Does that sounds like it covers everything? I have some interaction terms too. Also, what tests I can use?

Improve this question
$\endgroup$
2
  • $\begingroup$ Thank you. That was all the confirmation I required. Thanks very much! $\endgroup$
    – user52466
    Commented Jul 21, 2014 at 14:36
  • $\begingroup$ Fair enough, I'll make it an official answer. $\endgroup$
    – gung - Reinstate Monica
    Commented Jul 21, 2014 at 14:47

1 Answer 1

Reset to default
1
$\begingroup$

Your suggestion doesn't make sense. If your response variable is 0/1, then you should use logistic regression or probit. (If you want help understanding the distinction between them, it may help you to read my answer here: Difference between logit and probit models.) You can include interactions as you like. The model output will come with Wald tests of the parameters without your having to do anything else.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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