I've watched videos, read articles, asked around, but I can't seem to get into my head how exactly multiple regression works.

I mostly use logistic multiple regression and so I will have a binary dependent variable and various independent variables.

I know that if my dependent variable is weight and my independent variables are exercise, times per month at McDonalds and amount of soda in per month, the answers I will get is:

"McDonalds affects weight in this way, controlling for soda per month and whether people exercise"

How it does this (preferably explained without too much mathematics) is very hard for me to grasp. Does the model look at the relationship between McDonalds and weight by putting the 'average' values for soda and exercise in the model?

Duplicate report edit: I'm not asking how to control for variables nor what it means, I am asking specifically how regression do it.


marked as duplicate by mkt - Reinstate Monica, COOLSerdash, Michael R. Chernick, whuber regression Oct 2 at 16:38

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

  • 1
    $\begingroup$ Regarding your edit, some of the answers at the proposed duplicate address that. If you could clarify what about your question is not addressed there, it would be helpful. $\endgroup$ – mkt - Reinstate Monica Oct 2 at 14:42