Hi,
I'm interested in studying the impact of body mass index at baseline on blood pressure measured 10 years later. I'm also interested in studying the impact of change in body mass index from baseline to Year 3 and its impact on blood pressure measured at year 10. My models are first adjusted for age, sex and education.
I have been told by a colleague that I should do a linear mixed regression instead of a linear regression because of the adjustment. However, I don't understand why at all. I have always been told to use mixed models for hierarchical data or repeated data over time. I don't see at all why a mixed model in this case instead of a classic linear model.
This forum is maybe not the most relevant but I'm programming on STATA. I think it's a very basic question.

Anyone to help me? Thank you very much for your help!

Cheng