How to remove an interaction term from a regression?

Hello everyone,

Following my question here, I am looking for a way to drop an interaction term that is the interaction of one category of a categorical variable (say sex_Male) and another category of another categorical variable (say, frame_demand).

Is it possible to remove this specific interaction (sex_Male:frame_demand) and not the whole interaction between two categorical variables (sex:frame) or not the the categories (sex_Male or frame_demand)?

Thanks!

Mostafa

Answer 1

[Mostafa]

I found the solution and instead of deleting the question, I am writing my answer to help someone else who may face the same issue.

In order to remove specific interactions from a regression, I converted all categorical variables into dummy variables. We now have a variable associated with each category whose interaction can be easily excluded from the model specification (The reference categories must also be excluded, obviously).

I excluded the problematic interaction from the formula and it worked without any rank deficient error either with or without random-effect.

[dpb]

@Mostafa -- good idea to post the solution; I'd just comment it would be of more general help to others if were to include sample code to illustrate besides the verbal explanation. I would then recommend to post that as an Answer rather than a Comment. Just a suggestion... :>)