Principal Stratification in Causal Inference

By C. Frangakis, Donald B. Rubin. 2002

1,613 citations recorded by the source corpus.

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

The Econometrics of Randomized Experiments (2016, methodology): “An alternative approach that deals directly with the non-compliance is to use instrumental variables methods and related methods based on principal stratification (Frangakis and Rubin, 2002; Barnard, Du, Hill, and Rubin, 1998).”
Causal inference in statistics: An overview (2009, background): “These equivalence classes were later called “principal stratification” by Frangakis and Rubin (2002). Looser bounds were derived earlier by Robins (1989) and Manski (1990).”
Decomposing Treatment Effect Variation (2016, methodology): “Following Angrist, Imbens, and Rubin (1996) and Frangakis and Rubin (2002), we can classify units into four compliance types based on the joint values of Di(1) and Di(0): Ui = ⎧⎪⎪⎨⎪⎪⎩ Always Taker (a) if Di(1) = 1,Di(0) = 1, Never Taker (n) if Di(1) = 0,Di(0) = 0, Complier (c) if Di(1) = 1,Di(0) =…”
Emoticons vs. Emojis on Twitter: A Causal Inference Approach (2015, methodology): “2007) and stratification (Frangakis and Rubin 2002).”
Estimation of Causal Effects via Principal Stratification When Some Outcomes are Truncated by “Death” (2003, methodology): “This partition of the students is a direct application of the idea of principal stratification (Frangakis and Rubin, 2002) using the framework of the “Rubin Causal Model.””
Statistical Causality from a Decision-Theoretic Perspective (2014, methodology): “The DT approach also fosters healthy scepticism of other methods, such as “principal stratification” (Frangakis and Rubin 2002), that depend crucially on the philosophically perplexing assumption of the real simultaneous existence of potential response pairs (Dawid and Didelez 2012), together with n”
Differential effects of high‐quality child care (2002, background): “Because these child care groups correspond to a somewhat simple example of what Frangakis and Rubin (2002) call “principal strata” (because they stratify the population into mutually exclusive subgroups based on theoretical pre-treatment variables), these three groups will be referred to henceforth…”
Structural nested models and G-estimation: the partially realized promise (2014, background): “Joffe, Small and Hsu (2007) consider the relation between these retrospective models and the popular approach of principal stratification (Frangakis and Rubin (2002)).”
Causality: a Statistical View (2004, background): “For a further discussion of surrogates and related issues, see Frangakis & Rubin (2002) and Lauritzen (2003).”
Using Secondary Outcomes to Sharpen Inference in Randomized Experiments With Noncompliance (2013, background): “Recent literature on instrumental variables (IV; Imbens and Angrist 1994; Angrist et al. 1996) and principal stratification (Frangakis and Rubin 2002) shows that in these settings one can identify the causal effect of assignment among compliers, subjects who would take the treatment if offered to…”
The calibration of treatment effects from clinical trials to target populations (2009, background): “For this reason, these strata are known as ‘principal strata’ [8].”
Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes (2019, background): “We assume treatments X1, X2, states S1, S2 and primary outcome Y are all binary variables; values of each variable are decided by their corresponding unobserved counterfacutals S2x1 , X2x1 , Yx̄2 following definitions in [3, 9].”
A review of instrumental variable estimators for Mendelian randomization (2015, background): “In the language of principal stratification for randomized trials, this is equivalent to the assumption that there are no defiers.(21) For genetic variants that have proven biological links with the risk factor, the monotonicity assumption is plausible, as such biological effects seem likely to act ”