|
|
Unconditional GMM for Nested Data |
|
Message/Author |
|
Anne Chan posted on Tuesday, August 04, 2015 - 9:56 am
|
|
|
I would like to run a unconditional GMM (i.e., no covariates and no distal outcomes), which classified students into groups according to their motivational trajectories. The students are nested within schools. How should I accounted for the nested nature of the data in the analysis? As I am running a unconditional GMM, example 10.9 (which involves covariates at school level) seems to be not applicable to our case. I tried the "CLUSTER =" option with "Type = Complex Mixture". The model output looks ok. Just wanted to confirm if this is the correct way to do it. Thanks! |
|
|
COMPLEX MIXTURE can be used to control for non-independence of observations due to clustering. |
|
Back to top |
|
|