This is actually a surprisingly difficult problem. It is still an area of active research and no concensus has yet been reached. Here is one approach (I am not unbiased): http://www.stata-journal.com/article...article=st0182
Hi everbody,
It's my first post and I hope I posted in the right forum.
In my master thesis I use binary logistic regression:
a dichotomous variable as dependent variable, and four ratio scaled variables as independent variables.
2 of the independent variables turns out as significant predictors (Let's call them Var A and Var B.)
But there are doubts that there could be a mediation effect. As mediator Var A might affect the relation between Var B and the dependent variable.
Now to my question. How do I control mediators in a logistic regression? How does a mediation analysis in logistic regression work?
In a linear regression you can residualize the influence, but I do work with a logistic regression. I paid attention to the correlation between Var A and Var B, which was moderate (0.5). But I am not sure, if that's enough of controlling.
I'm thankful for every answer.
Best regards Frodo
This is actually a surprisingly difficult problem. It is still an area of active research and no concensus has yet been reached. Here is one approach (I am not unbiased): http://www.stata-journal.com/article...article=st0182
You may also have some luck looking in genetic research. That is where I have seen some good literature. In particular the presence of certain genes and their mediating effects.
Stop cowardice, ban guns!
Tweet |