rgm smeets posted on Tuesday, February 05, 2019 - 2:20 pm
Dear Mister Muthen,
I ran a LCA with individually measured variables in a dataset of more than 10k patients. Some patients belong to the same family and are therefore not independent of each other. As we use the LCA as an observational and explorative clustering technique, I would argue that the non-independence is acceptable. What is your opinion about this?