Ahn Jaeil, Liu Suyu, Wang Wenyi, Yuan Ying
Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas, 77030, U.S.A.; Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, Texas, 77030, U.S.A.
Biometrics. 2013 Dec;69(4):914-24. doi: 10.1111/biom.12100. Epub 2013 Nov 6.
The analysis of longitudinal dyadic data is challenging due to the complicated correlations within and between dyads, as well as possibly non-ignorable dropouts. Based on a mixed-effects hybrid model, we propose an approach to analyze longitudinal dyadic data with non-ignorable dropouts. We factorize the joint distribution of the measurement and dropout processes into three components: the marginal distribution of random effects, the conditional distribution of the dropout process given the random effects, and the conditional distribution of the measurement process given the random effects and missing data patterns. We model the conditional dropout process using a discrete survival model, and the conditional measurement process using a latent-class pattern-mixture model. These models account for the dyadic interdependence using the "actor" and "partner" effects and dyad-specific random effects. We use the latent-dropout-class approach to address the problem of a large number of missing data patterns caused by the dyadic data structure. We evaluate the performance of the proposed method using a simulation study, and apply our method to a longitudinal dyadic data set that arose from a prostate cancer trial.
由于二元组内部和之间存在复杂的相关性，以及可能存在不可忽视的失访情况，纵向二元组数据分析具有挑战性。基于混合效应混合模型，我们提出了一种分析存在不可忽视失访情况的纵向二元组数据的方法。我们将测量和失访过程的联合分布分解为三个部分：随机效应的边际分布、给定随机效应的失访过程的条件分布，以及给定随机效应和缺失数据模式的测量过程的条件分布。我们使用离散生存模型对条件失访过程进行建模，使用潜在类别模式混合模型对条件测量过程进行建模。这些模型使用“个体”和“伙伴”效应以及特定二元组的随机效应来考虑二元组的相互依赖性。我们使用潜在失访类别方法来解决由二元组数据结构导致的大量缺失数据模式问题。我们通过模拟研究评估所提出方法的性能，并将我们的方法应用于一个源自前列腺癌试验的纵向二元组数据集。
