Replicating a CFA using summary data PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 jmquinn posted on Wednesday, June 04, 2014 - 6:41 pm
Good afternoon,

I am attempting to replicate a published study using their supplied correlation matrix and means and standard deviations, and I keep getting the following error message after specifying this input:

Data:
FILE IS "matrix3_2014.txt";
TYPE IS CORR MEANS STDEVIATIONS ;
NOBSERVATIONS = 122;

variable:
NAMES ARE V1-V6;
USEVARIABLES ARE ALL;

model:
Y1 BY V1-V3;
Y2 BY V4-V5;
V6 on Y1 Y2;

Y1 WITH Y2;


*** ERROR
One or more variables have a variance of zero.

Variable Variance

VOC 0.146
LSK 0.380
BURT 0.660
**WRAT 0.000
**LC 0.000
RC 0.889

Since this is summary data, why am I getting this error message? Thank you for your help!
 jmquinn posted on Wednesday, June 04, 2014 - 6:43 pm
I apologize, I was trying to blind the variable names at the bottom. Those correspond to V1-V6.
 jmquinn posted on Wednesday, June 04, 2014 - 7:37 pm
good news, I figured out my issue.

For those who read this at a later time and wonder the same thing: try to use a full correlation matrix instead and specify FULLCORR. that fixed it for me, though there may have been another way to fix it using the partial matrix.
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: