G-computation estimation for causal inference with complex longitudinal data
G-computation estimation for causal inference with complex longitudinal data
复制标题
DOI：
10.1016/j.csda.2006.06.016
复制
发表时间：
2006-12-01
影响因子：
1.8
通讯作者：
van der Laan, Mark J.
中科院分区：
文献类型：
--
作者：
Neugebauer, Romain;van der Laan, Mark J.
在一篇配套论文中[Neugebauer，R.，货车德兰，M. J.，2006年b。纵向研究中的因果效应：定义和最大似然估计。Comput. Stat.数据分析：这个问题，doi：10.1016/j.csda.2006.06.013]，我们提供了纵向研究中边际结构模型（MSM）因果效应定义的概述。描述了参数MSM（PMSM）和非参数MSM（NPMSM）方法，用于在时间依赖性结局的治疗效应汇总或分层分析中代表因果效应。详细描述了这些因果效应的最大似然估计（也称为G计算估计）。在本文中，我们开发了新的算法，实现的G-计算估计的NPMSM和PMSM的因果关系。目前的算法依赖于所有可能的治疗特定结果的蒙特卡罗模拟，也称为反事实或潜在结果。在（a）连续治疗研究和/或（B）长期随访（有或无时间依赖性结局）的纵向研究中，该任务在计算上变得不切实际。所提出的算法解决了这一重要的计算限制固有的G-计算估计在大多数纵向研究。最后，实际考虑所提出的算法导致NPMSM因果效应的定义的进一步推广，以使这些方法更可靠的应用到更广泛的现实生活中的研究。两个模拟研究的结果进行了说明。(c)2006 Elsevier B. V.保留所有权利。
In a companion paper [Neugebauer, R., van der Laan, M.J., 2006b. Causal effects in longitudinal studies: definition and maximum likelihood estimation. Comput. Stat. Data. Anal., this issue, doi: 10.1016/j.csda.2006.06.013], we provided an overview of causal effect definition with marginal structural models (MSMs) in longitudinal studies. A parametric MSM (PMSM) and a non-parametric MSM (NPMSM) approach were described for the representation of causal effects in pooled or stratified analyses of treatment effects on time-dependent outcomes. Maximum likelihood estimation, also referred to as G-computation estimation, was detailed for these causal effects. In this paper, we develop new algorithms for the implementation of the G-computation estimators of both NPMSM and PMSM causal effects. Current algorithms rely on Monte Carlo simulation of all possible treatment-specific outcomes, also referred to as counterfactuals or potential outcomes. This task becomes computationally impracticable (a) in studies with a continuous treatment, and/or (b) in longitudinal studies with long follow-up with or without time-dependent outcomes. The proposed algorithms address this important computing limitation inherent to G-computation estimation in most longitudinal studies. Finally, practical considerations about the proposed algorithms lead to a further generalization of the definition of NPMSM causal effects in order to allow more reliable applications of these methodologies to a broader range of real-life studies. Results are illustrated with two simulation studies. (c) 2006 Elsevier B.V. All rights reserved.