I am trying to run a latent class analysis with covariates using polca package. However, every time I run the model, the multinomial logit coefficients result different. I have considered the changes in the order of the classes and I set up a very high number of replications (nrep=1500). However, rerunning the model I obtain different results. For example, I have 3 classes (high, low, medium). No matter the order in which the classes are considered in the estimation, the multinomial model will give me different coefficient for the same combinations after different estimations (such as low vs high and medium vs high). Should I increase further the number of repetitions in order to have stable results? Any idea of why is this happening? I know with the function set.seed() I can replicate the results but I would like to obtain stable estimates to be able to claim the validity of the results. Thank you very much!
Asked
Active
Viewed 953 times
2 Answers
0
From the manual (?poLCA):
As long as probs.start=NULL, each function call will use different (random) initial starting parameters
you need to use set.seed() or set probs.start in order to get consistent results across function calls.
Jthorpe
- 9,756
- 2
- 49
- 64
-
Thank you! I know that I can use set.seed() but the results should converge to the same estimates with high number of repetition? otherwise the results I get are totally random. Therefore the estimates from the model are not stable, and I cannot make any claim about them. – coolwinter Nov 17 '15 at 18:57
0
Actually, if with different starting points you are not converging, you have a data problem.
LCA uses a kind of maximum likelihood estimation. If there is no convergence, you have an under-identification problem: you have too little information to estimate the number of classes that you have. Lower class numbers might run, or you will have to make some a-priori restrictions.
You might wish to read Latent Class and Latent Transition Analysis by Collins. It was a great help for me.
Lian
- 1
- 5