The unconditional latent growth curve model showed a good fit, log-likelihood (LL) χ2 = 204.27, df = 237, ns. For univariate model-fitted standardized residuals, overall LL χ2 = 7.21, df = 8, ns. There were a significant positive linear slope (µ̂ =1.04, SE = 0.13, p < .001) and a negative quadratic slope (µ̂ = −0.09, SE = 0.01, p < .001), suggesting a linear increase of the latent continuous response variable that represents individuals’ liability of having any alcohol abuse through adolescence, which decelerated slightly post-high school. Translating the rates of linear growth into the observed binary outcome, it suggested that the odds of adolescents having any alcohol abuse relative to no abuse increased by 2.83 (e1.04) per 1 year increase. The estimated variance of the intercept and linear slope were significant. Adolescents differed significantly from each other regarding their initial latent liability for alcohol abuse at grade 7 (σ̂2 = 7.79, SE = 1.32, p < .001) and rates of linear increase (σ̂2 = 0.35, SE = 0.06, p < .001). The intercept and linear slope were significantly
