A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect

@article{Robins1986ANA,
  title={A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect},
  author={James M. Robins},
  journal={Mathematical Modelling},
  year={1986},
  volume={7},
  pages={1393-1512}
}
  • J. Robins
  • Published 1986
  • Medicine
  • Mathematical Modelling
Abstract In observational cohort mortality studies with prolonged periods of exposure to the agent under study, it is not uncommon for risk factors for death to be determinants of subsequent exposure. For instance, in occupational mortality studies date of termination of employment is both a determinant of future exposure (since terminated individuals receive no further exposure) and an independent risk factor for death (since disabled individuals tend to leave employment). When current risk… Expand
A graphical approach to the identification and estimation of causal parameters in mortality studies with sustained exposure periods.
  • J. Robins
  • Medicine
  • Journal of chronic diseases
  • 1987
TLDR
The analytic approach introduced in this paper may be necessary to control bias in any epidemiologic study in which there exists a risk factor which both determines subsequent exposure and is determined by previous exposure to the agent under study. Expand
Addendum to “a new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect”
Viewed abstractly, the data from a longitudinal epidemiologic study consists of a string of numbers. These numbers represent for each study subject a series of empirical measurements (for example,Expand
Marginal Structural Models to Estimate the Joint Causal Effect of Nonrandomized Treatments
Even in the absence of unmeasured confounding factors or model misspecification, standard methods for estimating the causal effect of time-varying treatments on survival are biased when (a) thereExpand
Identification and estimation of survivor average causal effects
In longitudinal studies, outcomes ascertained at follow-up are typically undefined for individuals who die prior to the follow-up visit. In such settings, outcomes are said to be truncated by deathExpand
Identification and estimation of causal effects with outcomes truncated by death
TLDR
It is shown that the survivor average causal effect is identifiable with use of a substitution variable in place of the latent membership in the always-survivor group, and proposed novel model parameterizations for estimation of the survivorAverage causal effect under the authors' identification assumptions. Expand
Healthy worker survivor bias: implications of truncating follow-up at employment termination
TLDR
G-estimation together with weighting did not prevent selection bias due to employment termination, however, the bias might be avoided in studies with measured health-related variables on the pathway from health status toemployment termination. Expand
Doubly Robust and Efficient Estimation of Marginal Structural Models for the Hazard Function
TLDR
A pooled targeted maximum likelihood estimator is presented, offering bias reduction over the incumbent IPTW estimator when treatment probabilities may be misspecified and the substitution principle rooted in the TMLE potentially mitigates the sensitivity to large treatment weights in IPTW. Expand
Survivor average causal effects for continuous time: a principal stratification approach to causal inference with semicompeting risks
In semicompeting risks problems, nonterminal time-to-event outcomes such as time to hospital readmission are subject to truncation by death. These settings are often modeled with illness-death modelsExpand
A Comparison of Methods to Estimate the Hazard Ratio Under Conditions of Time-varying Confounding and Nonpositivity
TLDR
Using Monte Carlo simulation, the degree to which crude, work-status adjusted, and weighted (marginal structural) Cox proportional hazards models are biased in the presence of time-varying confounding and nonpositivity is assessed. Expand
Estimating Counterfactual Risk Under Hypothetical Interventions in the Presence of Competing Events: Crystalline Silica Exposure and Mortality From 2 Causes of Death
TLDR
Risks from both lung cancer and nonmalignant respiratory disease mortality would have been considerably lower if historical silica exposures in this cohort had not exceeded current regulatory limits. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 18 REFERENCES
Some confounding factors in the study of mortality and occupational exposures.
  • E. Gilbert
  • Medicine
  • American journal of epidemiology
  • 1982
TLDR
Data from the Hanford nuclear facility population (southeastern Washington State, 1947-1976), which includes many radiation workers, are used to illustrate a method for examining the effect on mortality of such potentially confouding variables as calendar year, length of time since entering the industry, employment status,length of employment, job category, and initial employment year. Expand
Multiplicative Models and Cohort Analysis
Abstract Three methods of cohort analysis are presented for a statistical model wherein the explanatory or exposure variables act multiplicatively on age × calendar year specific death rates. TheExpand
Exposure opportunity in case-control studies.
  • C. Poole
  • Medicine
  • American journal of epidemiology
  • 1986
TLDR
It is shown that disparities of exposure opportunity between cases and controls exert no bias on estimates of the incidence rate ratio and such indicators are not confounders; therefore, they do not need to be controlled in the design or analysis of case-control studies. Expand
General relative-risk models for survival time and matched case-control analysis
A general likelihood is derived for survival time and matched case-control analysis. It allows alternatives to the usual exponential dependence of relative risk on exposure variables; instead thisExpand
Confounding: essence and detection.
TLDR
In case-referent studies confounding can arise in two ways: a priori confounders are correlates of exposure in the joint source population of cases and reference subjects; also, they are determinants of diagnosing the illness or have different selection implications between cases and referents. Expand
Lung cancer mortality among U.S. uranium miners: a reappraisal.
TLDR
Examination of lung cancer mortality among a cohort of white underground uranium miners in the Colorado plateau finds that differences between miners' and nonminers' mortality rates are substantially higher for smokers than for nonsmokers. Expand
On the Nature and Discovery of Structure
Abstract Extending principles of experimentation, we discuss conditions under which nonexperimental data allow consistent estimation of effects of the kind revealed by experimentation and relevant toExpand
Estimation of Response Probabilities From Augmented Retrospective Observations
TLDR
The problem of identification is analyzed and the need for statistically sound and computationally tractable estimation methods to be available is presented. Expand
Case-control studies for the evaluation of screening.
The case-control approach has been proposed for the evaluation of the efficacy of screening for cancer. It provides information at the level of the individual subject and allows direct estimation ofExpand
Arsenic and respiratory cancer in man: an occupational study.
TLDR
The hypothesis that inhaled arsenic is a respiratory carcinogen in man, but an inRuence of sulfur dioxide or unidentified chemicals, varying concomitantly with arsenic exposure, cannot be discounted is supported. Expand
...
1
2
...