|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
LGM with a multivariate outcome |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
|
Hi there, I am just considering running a LGM model where the outcome is defined by a 3-part composition. How should I express this in my model? An example would be model physical activity over time. Physical activity is better defined by a composition of sedentarism, light activity, and mvpa. So all three should be modeled at the same time, controlling for each other. I am not sure if running a normal model on, say MVPA and then control for time-varying light and sed would do the job. Any thoughts on this? thanks! Borja |
|
|
Why not try using a single factor measured by the 3 parts. |
|
Back to top |
|
|