| Message/Author |
|
|
| Ashley posted on Sunday, May 28, 2017 - 9:20 pm
|
|
|
Hello,
I'm attempting to model Multiple-Group Measurement Invariance in CFA to test a higher order CFA for model variance across groups (e.g., urban/rural setting) on an imputed dataset. The model is a mix of continuous and dichotomous variables. I keep getting the following error:
*** ERROR
The following MODEL statements are ignored:
* Statements in the GENERAL group:
[ X4 ]
[ X5 ]
[ X7 ]
[ X8 ]
[ X10 ]
[ X11 ]
[ X12 ]
[ X13 ]
[ X14 ]
[ X15 ]
* Statements in Group URBAN:
[ X4 ]
[ X5 ]
[ X7 ]
[ X8 ]
[ X10 ]
[ X11 ]
[ X12 ]
[ X13 ]
[ X14 ]
[ X15 ]
The list of variables is all of the dichotomous variables in my model. Any advice on how I could fix the error would be greatly appreciated. Thank you! |
|
|
|
|
The removed statements refer to mean. Dichotomous variables have a threshold not a mean. A threshold is referred to as follows:
[ X4$1 ] |
|
|
| Ashley posted on Monday, May 29, 2017 - 11:45 am
|
|
|
Thank you. I corrected this and I am now getting the following message:
THE MODEL ESTIMATION TERMINATED NORMALLY
THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE
COMPUTED. THE MODEL MAY NOT BE IDENTIFIED. CHECK YOUR MODEL.
PROBLEM INVOLVING THE FOLLOWING PARAMETER:
Parameter 79, Group URBAN: x4
THE CONDITION NUMBER IS -0.145D-15.
x4 is the first dichotomous variable in the model. Any thoughts on how I can fix this would be greatly appreciated. Thank you! |
|
|
|
|
| Please send the output and your license number to support@statmodel.com. |
|
|
| Back to top |
