I actually came across this, but this section "nb <- estim_ncpPCA(don,method.cv = "Kfold", verbose = FALSE)" produces only 1 component which is not in line with the scree plot for the PCA on the incomplete data. Is this okay? I am a bit confused by it.

How would you add a varimax rotation to this code?

Following Jeffrey-Raftery's (1995) guidelines, if the difference in BICs between the two models is 0–2, this constitutes ‘weak’ evidence in favor of the model with the smaller BIC; a difference in BICs between 2 and 6 constitutes ‘positive’ evidence; a difference in BICs between 6 and 10 constitutes ‘strong’ evidence; and a difference in BICs greater than 10 constitutes ‘very strong’ evidence in favor of the model with smaller BIC.

@PeterFlom this is reassuring. It all went back to being positive when I fixed the factor loadings and henceforth the model outputs were as expected. I'm assuming this model can be used then. Thank you for your help!

My point is - you fit the growth model on the scalar invariant measurement model, not on the unrestricted one.

@ChristianGeiser does that mean I should change the starting values? Thank you for your help!

Yes, that's what I meant. Only the signs at one of the time points changed to negative when I ran the longitudinal model. The remaining ones are all positive. I don't get why that happened.

Sorry for jumping on this post but do you fit the GMM on the restricted model or on the unrestricted one? What I mean is - you go through the process of establishing scalar measurement invariance, can you then use the unrestricted model for the remaining analysis or are you expected to use the restricted model?