Lin Haiqun, Guo Zhenchao, Peduzzi Peter N, Gill Thomas M, Allore Heather G
Division of Biostatistics, Yale University School of Public Health, New Haven, Connecticut, USA.
Biometrics. 2008 Dec;64(4):1032-42. doi: 10.1111/j.1541-0420.2008.01011.x. Epub 2008 Mar 19.
We propose a general multistate transition model. The model is developed for the analysis of repeated episodes of multiple states representing different health status. Transitions among multiple states are modeled jointly using multivariate latent traits with factor loadings. Different types of state transition are described by flexible transition-specific nonparametric baseline intensities. A state-specific latent trait is used to capture individual tendency of the sojourn in the state that cannot be explained by covariates and to account for correlation among repeated sojourns in the same state within an individual. Correlation among sojourns across different states within an individual is accounted for by the correlation between the different latent traits. The factor loadings for a latent trait accommodate the dependence of the transitions to different competing states from a same state. We obtain the semiparametric maximum likelihood estimates through an expectation-maximization (EM) algorithm. The method is illustrated by studying repeated transitions between independence and disability states of activities of daily living (ADL) with death as an absorbing state in a longitudinal aging study. The performance of the estimation procedure is assessed by simulation studies.
我们提出了一个通用的多状态转换模型。该模型用于分析代表不同健康状况的多种状态的重复发作情况。使用具有因子载荷的多元潜在特征对多种状态之间的转换进行联合建模。不同类型的状态转换通过灵活的特定转换非参数基线强度来描述。特定状态的潜在特征用于捕捉个体在该状态下停留的倾向，这种倾向无法由协变量解释，并用于解释个体在同一状态下重复停留之间的相关性。个体在不同状态下停留之间的相关性通过不同潜在特征之间的相关性来解释。潜在特征的因子载荷适应了从同一状态到不同竞争状态的转换的依赖性。我们通过期望最大化（EM）算法获得半参数最大似然估计。通过在一项纵向衰老研究中，以死亡为吸收状态，研究日常生活活动（ADL）的独立状态和残疾状态之间的重复转换来说明该方法。通过模拟研究评估估计程序的性能。
