Pls help me check on this path analys... PreviousNext
Mplus Discussion > Structural Equation Modeling >
 Kevin Huang posted on Monday, March 21, 2011 - 12:02 am
Hi All,

I am a beginning to Mplus. Will appreciate your help on my questions!

I am testing a model using path analysis. In my proposed model, I have 3 IVs (x1-x3), 2 mediators (y1, y2), and 4 DVs (y3-y6).

Here are the first code I wrote:

TITLE: test for model;
Data: file is TestData.dat;
Variable: Names are y1-y6 X1-X3;
Usevariables are y1-y6 X1-X3;
Model: y1 y2 ON x1-x3;
y3 y4 y5 y6 ON y1 y2;
y3 y4 y5 y6 ON x1 x2 x3;

The results were not quite good. CFI=.93, but RMSEA= .54. But another student used AMOS and ended up with a result of CFI= .94, RMSEA= .06. We are using the same dataset.

Did I do it right? Or, I was wrong on the code part?

 Linda K. Muthen posted on Monday, March 21, 2011 - 10:43 am
The difference in fit could be due to Mplus using n and Amos using n-1. Or the models could be different. Check the number of parameters in both outputs.
 Tony Reed posted on Monday, March 21, 2011 - 1:54 pm
thank you very much!! i actually messed sth up. now the result is very good!!thanks!!
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message