|
Message/Author |
|
|
Hello, I am running a latent class analysis on a dataset of 250 cases. I have 20 dichotomous variables that I would like to include in the LCA but am concerned about power. In your experience, is this too many variables for the number of cases? Is there a way to conduct a power analysis for LCA? Thank you. Sarah Dauber |
|
|
Twenty variables may be okay depending on the characteristics of the variables and how separated the classes are. Only a Monte Carlo study can determine this. |
|
Back to top |
|
|