Skip to main content
. Author manuscript; available in PMC: 2015 Jun 1.
Published in final edited form as: Am J Phys Anthropol. 2014 Jun;154(2):189–200. doi: 10.1002/ajpa.22492

Table 2.

Model-fitting Results

Model Comparison Hypothesis Overall Fit Fit of Nested Model
Log-likelihood df χ2 p Δχ2 Δdf Δp
1 None: Saturated model −17584.4 0
2 vs. 1 Latent growth model conforms to the dataa −17590.4 8 12.0 .15
3 vs. 2 Linear growth in males, i.e., middle time point = 0.5 −17598.1 12 27.4 .01 15.4 4 < .01
4 vs 2 Linear growth in females, i.e., middle time point = 0.5 −17630.3 12 91.8 < .01 79.8 4 < .01
5 vs. 2 Nonlinear growth, i.e., fixed time point at .53 in males and .63 in females −17593.3 16 17.9 .33 5.8 8 .67
6 vs 5 Equal parameters across co-twins and zygosity groups −17627.3 68 85.9 .07 68.0 52 .07
7 vs 6 No intercept-slope correlation −17628.9 74 89.0 .11 3.2 6 .78
8 vs 7 Intercept mean is equal between males and females −17644.8 75 120.9 < .01 31.8 1 < .01
9 vs 7 Intercept variance is equal between males and females −17645.8 75 122.8 < .01 33.8 1 < .01

Notes. Overall fit is in reference to the saturated model. Likelihood ratio test is based on twice the difference in log-likelihood values between nested models, which is distributed as chi-square; df = degrees of freedom.

a

Middle time point was freely estimated in all groups.