I would like to run a negative binomial regression, but also controlling for one of the variables. Similar to what you would do with a hierarchical regression. I am trying to predict violence (never, once, 3 times ...); and the literature says I should control for age, as aggression decreases with age. Would welcome your thoughts, thanks in advance. sharon

  • 4
    $\begingroup$ That seems fine, what is your question? $\endgroup$ – gung - Reinstate Monica Jun 13 '14 at 13:46
  • $\begingroup$ The question is how do I do this in 'stepwise format', if possible. Or do I simply enter age, in my case, in the same 'step' as the other predictor variables? thanks $\endgroup$ – Sharon Xuereb Jun 23 '14 at 10:35

Any major statistical package that allows you to do negative binomial regression should allow you to include one or more variables within the regression model, which allows you to control for those variables as you would in any other form of regression.

  • $\begingroup$ Thanks for that. I was thinking in a kind of stepwise regression manner, where you would put age (in my example) in the first step, and then continue with the variables you are focussing on in the next step. $\endgroup$ – Sharon Xuereb Jun 20 '14 at 14:24

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.