Effect size vs. baseline model PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 victor china posted on Sunday, July 29, 2007 - 6:16 am
i have a simple model:

MODEL:
fishery ON year;

in which fishery is categorial.

i am using ESTIMATOR = WLS

the effect size of the variable is significant (-3.957)

but the baseline model is rejected
X^2 = 15.659 , df=1 p=0.0001

what is the correct statistical inference from the output.

how can the effect size be significant and the model not?

thanks in advance

victor.
 Linda K. Muthen posted on Sunday, July 29, 2007 - 10:38 am
Model fit and the significance of parameter estimates are not the same. If you have a model that does not fit the data, the results of this model should not be interpreted.
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: