Table 1.
Fit and Parameters for Latent Growth Mixture Models
| # of classes | # of parameters | BIC | SABIC | −2LL | VLMR -2LL Difference | VLMR p-value | LMR -2LL Difference | LMR p-value | Entropy |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 18 | 9172.78 | 9115.64 | −4530.26 | -- | -- | -- | -- | -- |
| 2 | 23 | 9150.85 | 9077.85 | −4503.71 | 53.11 | .0002 | 51.46 | .0003 | 0.742 |
| 3 | 28 | 9124.60 | 9035.72 | −4474.99 | 59.09 | .0003 | 57.25 | .0003 | 0.785 |
| 4 | 33 | 9114.44 | 9009.70 | −4454.32 | 41.34 | .044 | 40.05 | .048 | 0.823 |
| 5 | 38 | 9044.11 | 8923.49 | −4403.56 | 42.15 | .438 | 40.84 | .447 | 0.924 |
Note. Boldface data reflect the best-fitting model based on fit criteria described earlier in the article. −2LL = −2 log likelihood; BIC = Bayesian Information Criteria; LMR = Lo-Mendell-Rubin Adjusted Likelihood Ratio Test; SABIC = Sample-Size Adjusted BIC; VLMR = Vuong-Lo-Mendell-Rubin Likelihood Ratio Test.