Starting value PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Wu wenfeng posted on Sunday, December 26, 2010 - 3:06 am
Dear Mplus team, in multilevel SEM, is there a simple methoed to find out good starting value? if there is, could you please show me how to do? thank you!
 Linda K. Muthen posted on Sunday, December 26, 2010 - 7:45 pm
In most cases, the default starting values of Mplus are sufficient. If there are convergence problems, Mplus automatically provides an input with starting values of the ending values on the incomplete estimation.
 Wu wenfeng posted on Sunday, December 26, 2010 - 10:55 pm
sorry! I'm not fully understand your meaning, do you mean Mplus don't need to set starting value by hand? if there is a convergence problem, the only reason is the model design, isn't it?
 Linda K. Muthen posted on Monday, December 27, 2010 - 12:00 pm
You do not need to give starting values in Mplus. Convergence problems can come for a variety of reasons. See convergence problems in the index of the user's guide for further information.
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: