Table 4.
Model | # Cl | # Params | LogLik | BIC | Entropy | Class Percentages |
---|---|---|---|---|---|---|
Mother Reports (Age 7–12) | ||||||
1. No Random Effects | 1 | 4 | −24172 | 48379 | ||
2 | 7 | −22520 | 45103 | .66 | 60, 40 | |
3 | 10 | −22169 | 44427 | .61 | 46, 36, 18 | |
4 | 13 | −22121 | 44359 | .63 | 45, 29, 22, 04 | |
5 | Failed to replicate likelihood | |||||
2. Random Intercept | 1 | 5 | −22189 | 44423 | ||
2 | Failed to converge | |||||
3. Random Intercept and Slope |
1 | 6 | −22189 | 44431 | ||
2 | Failed to replicate likelihood | |||||
Self-Reports (Age 14–18) | ||||||
4. No Random Effects | 1 | 4 | −4502 | 9033 | ||
2 | 7 | −4317 | 8687 | .60 | 67, 33 | |
3 | 10 | −4287 | 8650 | .50 | 43, 42, 15, | |
4 | 13 | −4283 | 8663 | .42 | 35, 28, 21, 16 | |
5. Random Intercept | 1 | 5 | −4291 | 8619 | ||
2 | Failed to replicate likelihood | |||||
6. Random Intercept and Slope |
1 | 6 | −4288 | 8622 | ||
2 | Failed to replicate likelihood | |||||
Piecewise Models (Age 7–18) | ||||||
7. Random intercept | 1 | 9 | −29596 | 59273 | ||
2 | 15 | −29545 | 59224 | .4 | 76, 24 | |
8. Rater Mean Difference = 0* |
1 | 8 | −29612 | 59297 |
Δχ2=25.4, df=1, p = 4.5E-8
Latent class growth models for maternal and self-ratings separately, and jointly using a piecewise model. Models were estimated with an increasing number of classes (Cl). Shown are the number of estimated parameters in the model, the final log likelihood value, the Bayesian information criterion (BIC), Entropy, and class proportions. Models with multiple classes did not have significantly lower BIC than models with a single class (bold). For the piecewise models, we selected a single class model because entropy was low indicating poor class assignment. Secondly, the BIC of the two class model fell within 1 SD of bootstrapped BIC for the single class model (BIC SD = 1142). Model 8 tested whether the second intercept was necessary to model the discontinuity between raters at ages 12 and 14. This was done by testing whether the mean of the second intercept could be set equal to 0. This model fit significantly worse than the unconstrained model, indicating a mean difference between raters.