Skip to main content
. Author manuscript; available in PMC: 2019 Jul 1.
Published in final edited form as: Prev Sci. 2018 Jul;19(5):620–629. doi: 10.1007/s11121-017-0783-3

Table 1.

Fit Information for Mothers’ and Fathers’ Latent Class Growth Analysis (LCGA) Models

Mothers
1 Class 2 Classes 3 Classes 4 Classes 5 Classes

Linear Quadratic Linear Quadratic Linear Quadratic Linear Quadratic Linear Quadratic
BIC 3800.968 3791.145 2913.816 2892.007 2344.824 2340.959 2332.510 2327.728 2341.461 2333.179
SABIC 3794.626 3781.632 2904.304 2879.323 2325.799 2315.592 2303.973 2289.678 2303.411 2282.445
VLMR p-Value N/A N/A < .001 < .001 .001 .012 .160 .172 .207 .549
aLMR p-Value N/A N/A < .001 < .001 .002 .019 .186 .186 .229 .568
Entropy N/A N/A .998 .999 .931 .929 .802 .844 .727 .772
Fathers
1 Class 2 Classes 3 Classes 4 Classes 5 Classes

Linear Quadratic Linear Quadratic Linear Quadratic Linear Quadratic Linear Quadratic
BIC 2763.427 2746.269 2288.223 2259.289 1733.821 1731.523 1725.388 1726.901 1736.800
SABIC 2757.091 2736.765 2278.718 2246.617 1714.812 1706.178 1696.875 1688.883 1698.782
VLMR p-Value N/A N/A < .001 < .001 .005 .004 .043 .185 .271
aLMR p-Value N/A N/A < .001 < .001 .009 .008 .060 .217 .301
Entropy N/A N/A .998 .999 .937 .943 .898 .900 .750

Note. BIC: Bayesian information criterion, SABIC: sample size adjusted Bayesian information criterion, VLMR: Vuong-Lo-Mendell-Rubin likelihood ratio test, aLMR: Lo-Mendell-Rubin adjusted likelihood ratio test. The BIC and SABIC consider fit and parsimony, with lower values being favored. A nominal significance level of .05 was used to evaluate the VLMR and aLMR likelihood ratio tests. For fathers, the five-class solution fitting a quadratic growth model in each class yielded an improper solution.