Multiple imputation of longitudinal categorical data through bayesian mixture latent Markov models.

Multiple imputation of longitudinal categorical data through bayesian mixture latent Markov models.
复制标题

DOI:
10.1080/02664763.2019.1692794
复制
发表时间:
2020
影响因子:
1.5
通讯作者:
Van Deun, Katrijn
Van Deun, Katrijn
中科院分区:
数学4区
文献类型:
--
作者:
Vidotto, Davide;Vermunt, Jeroen K.;Van Deun, Katrijn

文献摘要

参考文献

被引文献

相似文献

标准潜类模型最近被证明为横断面研究中缺失的分类协变量的多重imputation (MI)提供了一种灵活的工具。本文介绍了一种类似的纵向研究工具:使用贝叶斯混合潜马尔可夫(BMLM)模型的MI。除了保留潜在类模型的优点,即尊重变量的(分类)测量尺度并保留测量场合中变量之间可能存在的复杂关系外,所提出的BMLM模型的马尔可夫依赖结构允许捕获相邻时间点之间的滞后依赖,而时间常数混合结构允许捕获所有时间点之间的依赖。以及检索时变变量和时间常数变量之间的关联。通过仿真研究和实证实验对BMLM模型的性能进行了评价,并与完整案例分析和实证分析进行了比较。结果表明,该方法在提取分析模型参数方面具有良好的性能。相比之下,相互竞争的方法只能对数据的某些方面提供正确的估计。
Standard latent class modeling has recently been shown to provide a flexible tool for the multiple imputation (MI) of missing categorical covariates in cross-sectional studies. This article introduces an analogous tool for longitudinal studies: MI using Bayesian mixture Latent Markov (BMLM) models. Besides retaining the benefits of latent class models, i.e. respecting the (categorical) measurement scale of the variables and preserving possibly complex relationships between variables within a measurement occasion, the Markov dependence structure of the proposed BMLM model allows capturing lagged dependencies between adjacent time points, while the time-constant mixture structure allows capturing dependencies across all time points, as well as retrieving associations between time-varying and time-constant variables. The performance of the BMLM model for MI is evaluated by means of a simulation study and an empirical experiment, in which it is compared with complete case analysis and MICE. Results show good performance of the proposed method in retrieving the parameters of the analysis model. In contrast, competing methods could provide correct estimates only for some aspects of the data.
DOI: 10.1111/j.1751-5823.2011.00160.x
发表时间: 2011-12-01
影响因子: 2
作者:
Maruotti, Antonello
通讯作者: Maruotti, Antonello
DOI: 10.1080/10705511.2014.937376
发表时间: 2015-07-03
影响因子: 6
作者:
Bacci, Silvia;Bartolucci, Francesco
通讯作者: Bartolucci, Francesco
DOI: 10.1027/1614-2241/a000146
发表时间: 2018-04-01
影响因子: 3.1
作者:
Vidotto, Davide;Vermunt, Jeroen K.;Van Deun, Katrijn
通讯作者: Van Deun, Katrijn
DOI: 10.3102/1076998618769871
发表时间: 2018-10
期刊: Journal of educational and behavioral statistics : a quarterly publication sponsored by the American Educational Research Association and the American Statistical Association
影响因子: --
作者:
Vidotto D;Vermunt JK;van Deun K
通讯作者: van Deun K
DOI: 10.1037//1082-989x.7.2.147
发表时间: 2002-06-01
影响因子: 7
作者:
Schafer, JL;Graham, JW
通讯作者: Graham, JW