Bayesian mixed model question?
Hello,
Say I'm interested in examining the relationship between height and weight and I have multiple measurements for each individual over the course of their life (say at 8 different time points). Would I use the regression model below if I was only interested in predicting weight from height regardless of time point ?
lmBF (Weight ~ height , data = test, whichRandom = "ID")
Slightly unsure as to whether this is the correct way to deal with the above scenario where there is clearly non-independent observations (8 weight and 8 height measurements per individual)? Does the which random= ID function cover this?
Any Help would be appreciated
- Gabriel
Comments
Hi Gabriel,
The not-so-subtle statistical practice in experimental psychology would be to average the 8 time points for each participant and conduct the regression/correlation on the averaged numbers. A more subtle approach would be to apply some sort of hierarchical model (you can consider this a mixed effects model). However, if the 8 measurements span a lifetime, and you know the ages of the participants, then it may also be possible to estimate the parameters of a function that describes how weight fluctuates across age. How detailed you want to model the data depends on your purpose.
Cheers,
E.J.
Adding to EJ,
On a syntax level, you would need to also specify "ID" in the formula itself.
lmBF (Weight ~ height + ID, data = test, whichRandom = "ID")Hi EJ and MSB,
Thank you both for the responses and clarification!
So is the lmBF model specified above the not-so subtle practice ?
In this case I don't actually need the model to be very detailed, it's just that I need to take into account the non-independent observations.
All the best,
Gabriel