Relation between three classes of structural models for the effect of a time-varying exposure on survival

被引:45
作者
Young, Jessica G. [1 ]
Hernan, Miguel A. [1 ,2 ]
Picciotto, Sally [1 ]
Robins, James M. [1 ,3 ]
机构
[1] Harvard Univ, Sch Publ Hlth, Dept Epidemiol, Boston, MA 02115 USA
[2] Harvard MIT, Div Hlth Sci & Technol, Cambridge, MA USA
[3] Harvard Univ, Sch Publ Hlth, Dept Biostat, Boston, MA 02115 USA
关键词
Causal inference; Survival analysis; Simulation; Marginal structural models; Structural nested models;
D O I
10.1007/s10985-009-9135-3
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Standard methods for estimating the effect of a time-varying exposure on survival may be biased in the presence of time-dependent confounders themselves affected by prior exposure. This problem can be overcome by inverse probability weighted estimation of Marginal Structural Cox Models (Cox MSM), g-estimation of Structural Nested Accelerated Failure Time Models (SNAFTM) and g-estimation of Structural Nested Cumulative Failure Time Models (SNCFTM). In this paper, we describe a data generation mechanism that approximately satisfies a Cox MSM, an SNAFTM and an SNCFTM. Besides providing a procedure for data simulation, our formal description of a data generation mechanism that satisfies all three models allows one to assess the relative advantages and disadvantages of each modeling approach. A simulation study is also presented to compare effect estimates across the three models.
引用
收藏
页码:71 / 84
页数:14
相关论文
共 15 条
  • [1] [Anonymous], 1984, Analysis of survival data
  • [2] Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men
    Hernán, MA
    Brumback, B
    Robins, JM
    [J]. EPIDEMIOLOGY, 2000, 11 (05) : 561 - 570
  • [3] Structural accelerated failure time models for survival analysis in studies with time-varying treatments
    Hernán, MA
    Cole, SR
    Margolick, J
    Cohen, M
    Robins, JM
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2005, 14 (07) : 477 - 491
  • [4] A structural approach to selection bias
    Hernán, MA
    Hernández-Díaz, S
    Robins, JM
    [J]. EPIDEMIOLOGY, 2004, 15 (05) : 615 - 625
  • [5] PAGE J, 2008, STRUCTURAL NESTED CU
  • [6] Picciotto S, 2008, AM J EPIDEMIOL, V167, pS139
  • [7] Picciotto S, 2009, AM J EPIDEMIOL, V169, pS34
  • [8] A NEW APPROACH TO CAUSAL INFERENCE IN MORTALITY STUDIES WITH A SUSTAINED EXPOSURE PERIOD - APPLICATION TO CONTROL OF THE HEALTHY WORKER SURVIVOR EFFECT
    ROBINS, J
    [J]. MATHEMATICAL MODELLING, 1986, 7 (9-12): : 1393 - 1512
  • [9] Robins J M., 1998, 1997 Proceedings of the Section on Bayesian Statistical Science, P1
  • [10] ROBINS JM, 1993, EPIDEMIOLOGY, V4, P189