|
|
 |
| Cross-lagged panel design |
 
|
| Message/Author |
|
|
|
|
Hello Dr/s Muthen,
I'm new to Mplus and wanted to confirm if my cross-lagged model (5 manifest, binary variables assessed twice) is correctly specified using WLSMV:
CATEGORICAL = X1-X5 Y1-Y5;
X1 ON SES;
X2-4 ON age gender SES;
Y1 ON SES;
Y2-4 ON age gender SES;
X1 WITH X2 X3 X4 X5;
X2 WITH X3 X4 X5;
X3 WITH X4 X5;
X4 WITH X5;
Y2 ON X2 X1;
Y1 ON X1 X2;
Y3 ON X3 X1;
Y1 ON X1 X3;
Y4 ON X4 X1;
Y1 ON X1 X4;
Y5 ON X5 X1;
Y1 ON X1 X5;
I'm uncertain whether I should declare X1-X5 as categorical or not as I read in previous comments that this command is related to dependent variables. However, given the estimation of autocorrelations I'm just wondering if it's necessary.
Thanks for your help in advance and kind regards! |
|
|
|
|
A variable is a DV if it is on the left-hand side of ON. If categorical, they should be so declared.
You say "X2-4" - do you mean X2-X4? What about X5? |
|
|
|
|
Thanks for your quick response. And you were right, it should have been:
X1 ON SES;
X2-X5 ON age gender SES;
Y1 ON SES;
Y2-Y5 ON age gender SES;
The variables of the cross-lagged model are just controlled for age, gender and SES at both assessments. However, X1-X5 are the predictors of interest in the cross-lagged model.
You suggest to declare X1-X5 as categorical, right? |
|
|
|
|
| Right. |
|
|
| Back to top |
|
|
