Hello dear Stata users,

I want to run a latent class analysis with 37 variables and approximately 70.000 observations. I want to try different number of classes, between 2 and 10. I have tried the gsem command with 2 classes but I see a not concave message and the model runs endlessly. I checked the help documentation of Stata and I tried to run a simpler model and use the estimates for initial values in my main model, I also restricted the number of iterations, I tried different method of maximisation. With these changes either my models are extremely slow, or when they run I still have missing standard errors. Have you ever faced a similar issue, and if so, could you share with me your experience please? I checked the FAQ but I couldn't find anything that could help. Thank you in advance.