Item errors correlate PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 yezi posted on Tuesday, September 06, 2011 - 6:10 pm
Hi,
When item errors correlate, how to compute the covariance of item errors in Mplus. I give an example. In the example the test has six items and item errors between item y1 and y3 correlate. I write the program as follows. Is the program right? In the programy1 with y3 indicate that item y1 and y3 correlate, and a7( that is h1) is the covariance of item errors between item y1 and y3, which equal 0.059. Can I understand that? Thank you very much.
 yezi posted on Tuesday, September 06, 2011 - 6:12 pm
Hi,
Program.
DATA: FILE IS p.dat;
VARIABLE: NAMES ARE y1-y6;
MODEL: f1 BY y1-y6*;
y1-y6 ;
y1 with y3(a7);
f1@1;
model constraint:
new(h1);
h1=a7;
 yezi posted on Tuesday, September 06, 2011 - 6:14 pm
output file

Two-Tailed
Estimate S.E. Est./S.E. P-Value
Y1 WITH
Y3 0.059 0.052 1.135 0.256
New/Additional Parameters
H1 0.059 0.052 1.135 0.256
 Linda K. Muthen posted on Wednesday, September 07, 2011 - 7:58 am
The parameter y1 WITH y3 is a residual covariances.
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: