Marginal Structural Models and Causal Inference in Epidemiology

By James M. Robins, Miguel A. Hern'an, Babette A. Brumback. 2000

5,693 citations recorded by the source corpus.

Subfields: Anatomy, Control and Systems Engineering, Statistics and Probability, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Anatomy

In Control and Systems Engineering

In Statistics and Probability

In Causal Inference & Discovery

Citations in the corpus

Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders (2019, methodology): “…to learn individualized treatment responses from longitudinal disease trajectories containing information about patient covariates and treatments assignments over time (Robins, 1986; Robins et al., 2000; Robins & Hernán, 2008; Soleimani et al., 2017; Schulam & Saria, 2017; Lim et al., 2018).”
Causal inference by using invariant prediction: identification and confidence intervals (2015, background): “…are the framework of potential outcomes and counter-factuals [cf. Dawid, 2000, Rubin, 2005]; or structural equation modelling [cf. Bollen, 1989, Robins et al., 2000, Pearl, 2009] and corresponding graphical modeling [cf. Lauritzen and Spiegelhalter, 1988, Greenland et al., 1999, Spirtes et…”
G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes (2020, methodology): “G-methods include gcomputation [4–6], structural nested models [7, 8], and marginal structural models [9, 10].”
Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations (2020, methodology): “To remove the association between time-dependent confounders and time-varying treatments, Marginal Structural Models propose using inverse probability of treatment weighting (IPTW).”
Handling time varying confounding in observational research (2017, methodology): “Three causal methods have been suggested for this purpose: inverse-probability-of-treatment weighting, 2 7-9 17 18 parametric G formula, 2 19 20 and G estimation.”
Learning When-to-Treat Policies (2019, methodology): “Perhaps the most straightforward approach to estimating Vπ starts from inverse propensity weighting as used in the context of marginal structural modeling (Precup 2000; Robins, Hernán, and Brumback 2000).”
Learning Representations for Counterfactual Inference (2016, background): “Counterfactual inference for determining causal effects in observational studies has been studied extensively in statistics, economics, epidemiology and sociology (Morgan & Winship, 2014; Robins et al., 2000; Rubin, 2011; Chernozhukov et al., 2013) as well as in machine learning (Langford et al.”
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes (2019, methodology): “While the NMDP model M1 is commonly the one assumed in the causal inference literature in the context of marginal structural model estimation (Robins, 2000; Robins et al., 2000) and DTRs (Chakraborty and Moodie, 2013; Murphy et al.”
Using Decision Lists to Construct Interpretable and Parsimonious Treatment Regimes (2015, background): “Assumption (A2) is automatically satisfied in a randomized study but is untestable in observational studies (Robins et al., 2000).”
Anchor regression: Heterogeneous data meet causality (2018, methodology): “variables are only available on the training, but not on the test data set. 2 2 Setting and notation We assume that the data are generated from a linear structural equation model (SEM) [Bollen, 1989, Robins et al., 2000, Pearl, 2009]. The overall goal is to predict the target variable Y 2R with the ”
Propensity score estimation: machine learning and classification methods as alternatives to logistic regression (2010, neutral): “Inverse probabilityeweighted marginal structural models [42,43] and some doubly robust models [44,45] similarly use propensity scores for reweighting observations to eliminate confounding and selection bias in observational settings.”
Generalizing evidence from randomized clinical trials to target populations: The ACTG 320 trial. (2010, methodology): “Next, we describe the use of inverse probability-of-selection weights, which are an extension of Horvitz-Thompson weights (29) and have been used extensively in survey sampling (30–32), for confounder control (33), and have been discussed in the context of selection bias (7, 19, 34, 35) or response ”
Does Job Loss Shorten Life? (2009, methodology): “We will adopt a propensity score weighted estimator similar to the estimators proposed in Robins, Hernán, and Brumback (2000), and Hirano and Imbens (2001).”
Semiparametric theory and empirical processes in causal inference (2015, methodology): “sein causalinferenceproblems.These includeverypowerfulmethodological tools that can be especially useful in causal settings. In Section 2 we give an introduction to causal inference, following Robins [38, 42, 54], van der Laan [54, 59, 63], and others. In order to answer causal questions with observ”