IRT model PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Ira Harvey Bernstein posted on Friday, July 01, 2011 - 2:58 pm
I have used Ex. 5.5 for conventional Samejima modeling of a nine-item test administered over 12 sessions. Because this is a clincal trial, there is nonrandom attrition so I feel most comfortable analyzing the data separately by sessions. I have three questions regarding version 6.11 output which I gather produces different output from previous versions.
1. Why does the output entitled "Chi-Square Test for MCAR under the Unrestricted Latent Class Indicator Model" appear on some outputs and not on others, apparently at random?
2. Why is there no CFI or TL descriptive output? I can understand why there is no RMSEA.
3. The results at week 0 for the Binary and Ordered Categorical Likelihood ratio Chi-squares are as follows:
Value 1962.712
Degrees of Freedom 1952731
P-Value 1.0000
These appear strange (similar values are found across the 12 sessions).
 Linda K. Muthen posted on Friday, July 01, 2011 - 3:32 pm
Please send the output and your license number to support@statmodel.com.
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: