|
|
| Message/Author |
|
|
| Riya Rai posted on Monday, July 23, 2018 - 4:15 pm
|
|
|
Hello all,
Our research project is investigating how trajectories of maternal depressive symptoms from gestation to eleven years postpartum impact child behavioural development at three time points in early to mid-childhood. We have a total of five dichotomized covariates. We are running a latent growth model on MPlus, and are getting the following error message:
THE MODEL ESTIMATION TERMINATED NORMALLY
THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES MAY NOT BE TRUSTWORTHY FOR SOME PARAMETERS DUE TO A NON-POSITIVE DEFINITE FIRST-ORDER DERIVATIVE PRODUCT MATRIX. THIS MAY BE DUE TO THE STARTING VALUES BUT MAY ALSO BE AN INDICATION OF MODEL NONIDENTIFICATION. THE CONDITION NUMBER IS 0.111D-18. PROBLEM INVOLVING PARAMETER: Parameter 135, Group INC: PARITY
However, when we try to get rid of our "parity" covariate, it will have the same warning message for another covariate. I would greatly appreciate any help I can get in fixing this. Thanks everyone. |
|
|
|
|
You can ignore the message if the variable is binary and you are "bringing the variable into the model" (by mentioning its mean, variance, or covariance with another variable).
If this doesn't help, send your output to Support along with your license number. |
|
|
| Back to top |
|
|
