Path Analysis PreviousNext
Mplus Discussion > Exploratory Factor Analysis >
Message/Author
 Toan Huu Ha posted on Thursday, October 22, 2009 - 4:55 pm
Hi,

I have a question. I run path analysis. One of the Est./S.E. is 1.56 (<1.96), but the StdYX is 0.71, can you explain why that happen ?.

Est./S.E. Std StdYX

1.561 0.063 0.711


Thank you
 Bengt O. Muthen posted on Thursday, October 22, 2009 - 5:21 pm
The estimated StdYX value is not necessarily related to the z score of Est./S.E. That is, you can get a non-significant z score for a rather large standardized value just because the SE is large.
 Toan Huu Ha posted on Thursday, October 22, 2009 - 5:59 pm
Thank you so much for your explaination.

In that case, can I still say that the path coefficient is good ( because high estimated StdYX ) even though Z score is not significant ?
 Bengt O. Muthen posted on Thursday, October 22, 2009 - 6:37 pm
No, you should go by the significance.
 Toan Huu Ha posted on Friday, November 06, 2009 - 6:39 pm
Hi,

I run path analysis and have Std and StdYX for path analysis model. As they differ, which value should I report ?

Thank you.
 Linda K. Muthen posted on Friday, November 06, 2009 - 7:08 pm
I would report StdYX for continuous covariates and StdY for binary covariates. See the STANDARDIZATION option in 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: