Bayesian inference for causal effects in randomized experiments with noncompliance

By Guido W. Imbens, Donald B. Rubin. 1997

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

The Econometrics of Randomized Experiments (2016, background): “This section builds on the discussions in Angrist (2004), Hirano, Imbens, Rubin, and Zhou (2000), Imbens and Rubin (1997ab) and Bertanha and Imbens (2014).”
Direct and Indirect Causal Effects via Potential Outcomes * (2004, methodology): “Such an assumption will greatly sharpen the multiple imputations that can be created for the missing potential outcomes (as illustrated in Imbens & Rubin, 1997; Hirano et al., 2000 A weaker assumption, but highly plausible in our case, is to allow causal effects of vaccination in all principal…”
Assessing the effect of an influenza vaccine in an encouragement design. (2000, methodology): “If we regard the N subjects in the study as a random sample from a much larger population, and the estimand is the corresponding average difference in this population, the independence assumption has little inferential effect for average treatment effects (Rubin, 1978; Imbens and Rubin, 1997a).”
Bayesian analysis of cross-section and clustered data treatment models (2000, background): “…analyzed in the econometrics and statistics literatures, often with di!erent nomenclatures to re#ect the setting of the problem (Copas and Li, 1997; Efron and Feldman, 1991; Imbens and Rubin, 1997; Heckman, 1978; Heckman and Robb, 1985; Holland, 1986; Lee, 1979; Maddala, 1983; Rubin, 1974,1978).”
Preventing Youth Violence and Dropout: A Randomized Field Experiment (2013, unknown): “…program, π 2 is a local average treatment effect (LATE) – the effect of the program (treatment) on those whose treatment receipt is affected by being assigned to the treatment rather than control group, or " compliers " (Angrist, Imbens & Rubin 1996; Imbens & Rubin 1997; Imbens & Angrist 1994)).”
The Causal Effect of Class Size on Academic Achievement (2011, methodology): “Using the ML approach, we estimate the causal effects more efficiently than can the 2SLS approach (Bollen, 1996; Imbens & Rubin, 1997a, 1997b; Little & Yau, 1998).”
Causal Inference With General Treatment Regimes (2004, background): “Although these distributions are sometimes appropriate in practice (e.g., Imbens and Rubin 1997), more often they are summarized by the relevant causal effect.”
The International Journal of Biostatistics Principal Stratification — a Goal or a Tool ? (2011, unknown): “̈ Robins and Greenland were the first to capitalize on this advantage and have used classification by response type as a cornerstone in many of their works, including confounding (1986) attribution (1988, 1989a,b) and effect decomposition (1992).”
Robust, accurate confidence intervals with a weak instrument: quarter of birth and education (2005, background): “One of the most compelling instances of an instrument occurs in randomized trials with non-compliance (e.g. Sommer and Zeger (1991), Sheiner and Rubin (1995), Goetghebeur and Molenberghs (1996), Imbens and Rubin (1997) and Heitjan (1999)).”
On the Predictive Distributions of Outcome Gains in the Presence of an Unidentified Parameter (2003, background): “…and Robb 1985; Björklund and Mof tt 1987; Heckman 1990; Manski 1990; Vijverberg 1993, Imbens and Angrist 1994; Heckman, Smith, and Clements 1997; Imbens and Rubin 1997; Koop and Poirier 1997; Abadie, Angrist, and Imbens 1998; Heckman and Smith 1998; Hahn 1998; Dehejia and Wahba 1999; Heckman…”
The design versus the analysis of observational studies for causal effects: parallels with the design of randomized trials (2007, methodology): “This model on the science completes the full model specification of all observable quantities as random variables, and so is the Bayesian approach, as defined first by Rubin [4] and further developed by Rubin [7] and in other places, such as Imbens and Rubin [20].”
Causal effects in clinical and epidemiological studies via potential outcomes: concepts and analytical approaches. (2000, methodology): “Rubin (57, 60, 62) provided a formal framework that extended the idea beyond randomized experiments and randomization-based inference; this extended framework also allows the formal consideration of complications, such as unintended missing data and noncompliance.”