I am running a series of univariate models before I combine my variables into a trivariate cholesky. I am running a full ACE model as well as nested AE, CE and E models and my AE is best fitting (not sure if this is important but I am only requesting CIs for my AE model since it is best-fitting). The following error messages consistently pop up under the output for AE. The output for the full ACE and other nested models does not show this error message.
1: In model 'univAE' while computing the lower bound for 'univAE.stPathEst_a[1,1]' NPSOL returned a non-zero status code 6. The model does not satisfy the first-order optimality conditions to the required accuracy, and no improved point for the merit function could be found during the final linesearch (Mx status RED)
2: In model 'univAE' while computing the lower bound for 'univAE.stPathEst_e[1,1]' NPSOL returned a non-zero status code 1. The final iterate satisfies the optimality conditions to the accuracy requested, but the sequence of iterates has not yet converged. NPSOL was terminated because no further improvement could be made in the merit function (Mx status GREEN).
3: In model 'univAE' NPSOL returned a non-zero status code 1. The final iterate satisfies the optimality conditions to the accuracy requested, but the sequence of iterates has not yet converged. NPSOL was terminated because no further improvement could be made in the merit function (Mx status GREEN).
I saw a previous post for the same error message and Dr. Neale stated this may mean the model is underidentified (as evidenced by identical -2LL). So, I changed the start values for all the models and came up with more of the same error messages. The best option (I think) is when I keep the start value for the AE .1 and the rest at 0. This gives me different -2LL and only one error message (the same one):
1: In model 'univAE' while computing the lower bound for 'univAE.stCovComp_E[1,1]' NPSOL returned a non-zero status code 6. The model does not satisfy the first-order optimality conditions to the required accuracy, and no improved point for the merit function could be found during the final linesearch (Mx status RED)
2: In model 'univAE' NPSOL returned a non-zero status code 1. The final iterate satisfies the optimality conditions to the accuracy requested, but the sequence of iterates has not yet converged. NPSOL was terminated because no further improvement could be made in the merit function (Mx status GREEN).
My (very limited beginner) understanding is that the code greens are ok, and that some code reds are ok as well. But I do not know how to distinguish whether this code red is ok for me to proceed with the rest of my analysis? Any help would be appreciated.
Thank you!