Categorical and Continuous mediators PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Seulki Choi posted on Tuesday, May 19, 2015 - 10:26 am
Dear Dr. Muthen

I have one categorical mediator, four continuous mediators, one categorical independent variable and one continuous dependent variable.

Cateogrical is m1;
Model:
m1 m2 m3 m4 m5 on x;
y on x m1 m2 m3 m4 m5;

In this case, should I use WLSMV?
or could you find example case that I can reference?

Thanks,
 Bengt O. Muthen posted on Tuesday, May 19, 2015 - 6:31 pm
Use WLSMV.
 Seulki Choi posted on Thursday, May 21, 2015 - 9:54 am
Dear Dr. Muthen

Thanks a lot.
I have one more question related with model fit.

I used modification indice and modified my model. However, I got

RMSEA
estimate 0.007
90 percent CI 0.000 0.096
probability RMSEA <= .05 0.65

CFI 1.000
TLI 0.998

Chisquare Test of Model Fit for Baseline Model
Value 465.816
DF 21
P value 0.000

Moreover I have 761 sample size.

Do you think I can report this as good fit and publish paper with even I have significant chisquare and RMSEA upper CI over 0.06?

What could you infer from this result? What do you think I can improve fit?

Thanks again
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: