Piecewise Linear Mixed Models With a Random Change Point

Welcome to the forum for runmlwin users. Feel free to post your question about runmlwin here. The Centre for Multilevel Modelling take no responsibility for the accuracy of these posts, we are unable to monitor them closely. Do go ahead and post your question and thank you in advance if you find the time to post any answers!

Go to runmlwin: Running MLwiN from within Stata >> http://www.bristol.ac.uk/cmm/software/runmlwin/
Post Reply
Posts: 1
Joined: Tue Nov 13, 2018 5:33 pm

Piecewise Linear Mixed Models With a Random Change Point

Post by SJKkeene724 »

Hello Bristol University,

I have no idea what to do here.

I have a cohort of patients with repeated measurements of BMI (kg/m^2) and smoking (current, former, never) across 10 years (1 measurement per year). I would like to start with just current smokers at baseline and see how the slope of their BMI (dependent variable) changes across time. I would also like to look at the slope in those patients who quit and become former smokers during follow-up. However, the time that this happens varies by patient and may not happen at all in some patients. Thus, a margin plot might have a single slope at first but then a branching off point representing when the BMI slopes separate between those who continue smoking and those who quit. I believe this is called Piecewise Linear Mixed Models With a Random Change Point (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5625953/)

I would like to stay away from Bayesian statistics for now if possible but I can try to learn. So, is there commands that can support this topic. I am sorry that this is so broad but I am in the beginning stages and have no idea what to do.

Thank you,

Post Reply