# of obs variable of each latent prof... PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Wong Yu-Jzun posted on Thursday, December 10, 2015 - 9:49 am
Dear£º
I'm just trying to simulate a LPA,with a question that how to set the number of observation variable of each latent profile£¿i use mplus v7, i know that "nobs=xx xx" command cant be used in type=mixture.so a SOS for you.
big thanks for your reply!
 Bengt O. Muthen posted on Thursday, December 10, 2015 - 2:47 pm
When you say

"the number of observation variable of each latent profile"

do you mean the number of people (or proportion) in each latent class?
 Wong Yu-Jzun posted on Thursday, December 10, 2015 - 4:32 pm
Sorry£¬i express in a wrong way.
Your understanding is right.And what command codes should be used to set the # of proportion in each latent class(cluster) under Monte Carlo command?
Thanks!
 Bengt O. Muthen posted on Saturday, December 12, 2015 - 4:57 pm
In the Overall part of the mixture model you give values for

[c#1*...];

Those are logits corresponding to the latent class probabilities. See end of the UG chapter 14 for how logits relate to probabilities.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: