The paper proposes a joint mixture model to model non-ignorable drop-out in longitudinal cohort studies of mental health outcomes. The model combines a (non)-linear growth curve model for the time-dependent outcomes and a discrete-time survival model for the drop-out with random effects shared by the two sub-models. The mixture part of the model takes into account population heterogeneity by accounting for latent subgroups of the shared effects that may lead to different patterns for the growth and the drop-out tendency. A simulation study shows that the joint mixture model provides greater precision in estimating the average slope and covariance matrix of random effects. We illustrate its benefits with data from a longitudinal cohort study that characterizes depression symptoms over time yet is hindered by non-trivial participant drop-out.

本文提出了一种联合混合模型来模拟心理健康结果纵向队列研究中不可忽视的辍学。该模型结合了时间相关结果的（非线性）增长曲线模型和辍学的离散时间生存模型，两个子模型共享随机效应。模型的混合部分通过考虑可能导致不同增长模式和辍学趋势的共享效应的潜在子组来考虑人口异质性。仿真研究表明，联合混合模型在估计随机效应的平均斜率和协方差矩阵方面提供了更高的精度。我们用纵向队列研究的数据说明了它的好处，该研究描述了抑郁症状随时间的变化，但受到非平凡参与者退出的阻碍。