Correcting for non-compliance in randomized trials using rank preserving structural failure time models

By James M. Robins, Anastasios A. Tsiatis. 1991

How researchers see this paper

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

Citations in the corpus

First-line crizotinib versus chemotherapy in ALK-positive lung cancer. (2014, unknown): “Stomatitis§ 24 (14) 1 (1) 34 (20) 2 (1)”
Structural nested models and G-estimation: the partially realized promise (2014, methodology): “By making a mapping between the potential outcomes themselves (rather than between distributions), such rank preserving SDMs are easier to understand and communicate.”
Overall Survival with Palbociclib and Fulvestrant in Advanced Breast Cancer (2018, unknown): “Doxorubicin 12 (5) 7 (4) 35 (27) 1 (1) 10 (9) 12 (14)”
Estimation in Partially Linear Models With Missing Covariates (2004, methodology): “This section contains results on asymptotic semiparametric ef ciency in the sense of Robins et al. (1994) in the iid setting given in Section 2.”
Mendelian randomization: Using genes as instruments for making causal inferences in epidemiology (2008, unknown): “These IV methods for binary outcomes have been used in econometrics and for determining causal effects in RCTs when there are non-compliers [9, 48, 118, 119], but not yet, to our knowledge, in Mendelian randomization studies.”
Estimating the effect of treatment in a proportional hazards model in the presence of non‐compliance and contamination (2007, methodology): “Robins and Tsiatis (1991) and others have developed methods that are based on accelerated failure models.”
An IV Model of Quantile Treatment Effects (2002, methodology): “This model is a special case of the IQT model, with assumption V4 corresponding to exact rank invariance or common error assumption A4* (see Doksum (1974), Robins and Tsiatis (1991) , Heckman and Smith (1997), and Vytlacil (2000) for various justifications of rank invariance), and V3 being a strong”
Essential Medical Statistics (2003, methodology): “A valid method to correct for non-adherence to treatment in randomized trials was developed by Robins and Tsiatis (1991), but has not been widely used in practice, partly because it is conceptually difficult.”
Demystifying Optimal Dynamic Treatment Regimes (2007, background): “Without further assumptions the optimal regime may only be estimated from among the set of feasible regimes (Robins, 1994): Let pj(aj |hj) denote the conditional probability of receiving treatment aj given history hj and let f(·) denote the density function of h2 = (x1, a1, x2).”
Phase 3 trial of everolimus for metastatic renal cell carcinoma (2010, methodology): “A post hoc exploratory OS analysis was performed using a rank-preserving structural failure time model to correct the treatment effect estimate for bias introduced by crossover from placebo to open-label everolimus after disease progression.(6,7) The rank-preserving structural failure time model pro”
Social Experiments and Instrumental Variables with Duration Outcomes (2005, background): “The non-parametric approach for effects on survival probabilities in our second main case is closely related to Imbens and Rubin (1997) and Abadie (2002), who discuss identification, estimation, and testing of distributional treatment effects in a non-parametric setting.”
On Instrumental Variables Estimation of Causal Odds Ratios (2011, methodology): “We refer the interested reader to Robins (1994) and Mullahy (1997) for inference on the conditional relative risk P(Y = 1|X,Z,C) P{Y (0) = 1|X,Z,C} ,(5) and to van der Laan, Hubbard and Jewell (2007) for inference on the so-called switch relative risk, which is defined as (5) for subjects with…”