Nathan Smith posted on Thursday, September 15, 2016 - 2:25 pm
Hello, I am estimating a growth curve model and trying to find the proper parametric curve that most appropriately fits the data. So, model 1 was an estimate of the intercept and slope only - bad model fit. Model 2 adds a quadratic - model fit improves significantly, but still bad. I try a model with a cubic - error message.
"THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE COMPUTED. THE MODEL MAY NOT BE IDENTIFIED. CHECK YOUR MODEL."
I check the problem parameter, its the variance of the intercept (wasn't a problem in the previous models). I would appreciate some help in understanding how to deal with this. My belief is that the cubic model will be better than the quadratic.