Using Secondary Outcomes to Sharpen Inference in Randomized Experiments With Noncompliance

@article{Mealli2013UsingSO,
  title={Using Secondary Outcomes to Sharpen Inference in Randomized Experiments With Noncompliance},
  author={Fabrizia Mealli and Barbara Pacini},
  journal={Journal of the American Statistical Association},
  year={2013},
  volume={108},
  pages={1120 - 1131}
}
  • F. Mealli, B. Pacini
  • Published 30 May 2013
  • Mathematics
  • Journal of the American Statistical Association
We develop new methods for analyzing randomized experiments with noncompliance and, by extension, instrumental variable settings, when the often controversial, but key, exclusion restriction assumption is violated. We show how existing large-sample bounds on intention-to-treat effects for the subpopulations of compliers, never-takers, and always-takers can be tightened by exploiting the joint distribution of the outcome of interest and a secondary outcome, for which the exclusion restriction is… 
Sharpening Bounds on Principal Effects with Covariates
TLDR
Whether bounds on principal effects can be improved by adjusting for a categorical baseline covariate is considered and adjusted bounds are considered which are shown to never be wider than the unadjusted bounds.
Using secondary outcome to sharpen bounds for treatment harm rate in characterizing heterogeneity
TLDR
The results show that a secondary outcome, which is more closely related to the primary outcome, can lead to narrower bounds and the application of the proposed bounds in a randomized clinical trial of determining whether the intensive glycemia could reduce the risk of development or progression of diabetic retinopathy.
Principal stratification analysis using principal scores
Practitioners are interested in not only the average causal effect of a treatment on the outcome but also the underlying causal mechanism in the presence of an intermediate variable between the
Causal Inference Methods For Addressing Censoring By Death And Unmeasured Confounding Using Instrumental Variables
This thesis considers three problems in causal inference. First, for the censoring by death problem, we propose a set of ranked average score assumptions making use of survival information both
Principal Score Methods: Assumptions and Extensions
Researchers addressing post-treatment complications in randomized trials often turn to principal stratification to define relevant assumptions and quantities of interest. One approach for estimating
Survivor-Complier Effects in the Presence of Selection on Treatment, With Application to a Study of Prompt ICU Admission
TLDR
The methods are applied in a UK cohort study of critical care patients to examine the mortality effects of prompt admission to the intensive care unit, using ICU bed availability as an instrument, along with nonparametric yet efficient estimation methods.
Treatment Effects on Ordinal Outcomes: Causal Estimands and Sharp Bounds
TLDR
Echoing recent advances in the econometrics and biostatistics literature, the sharp bounds of the aforementioned causal parameters for ordinal outcomes are presented, under fixed marginal distributions of the potential outcomes.
Post-Instrument Bias ∗
When using instrumental variables, researchers often assume that causal effects are only identified conditional on covariates. We show that the role of these covariates in applied research is often
Local Average and Quantile Treatment Effects Under Endogeneity: A Review
Abstract This paper provides a review of methodological advancements in the evaluation of heterogeneous treatment effect models based on instrumental variable (IV) methods. We focus on models that
Split-door criterion for causal identification: Automatic search for natural experiments
TLDR
This paper investigates a particular scenario in time series data that permits causal identification in the presence of unobserved confounders and presents an algorithm to automatically find such scenarios and shows that when both of these variables are caused by the same (unobserved) confounder, the problem of identification reduces to that of testing for independence among observed variables.
...
...

References

SHOWING 1-10 OF 75 REFERENCES
Assumptions when Analyzing Randomized Experiments with Noncompliance and Missing Outcomes
TLDR
The approach the authors follow differs from that based on standard “structural” econometrics models where non intuitive distributional and statistical assumptions are usually introduced to identify parameters of interest from observed data.
Bayesian inference for causal effects in randomized experiments with noncompliance
For most of this century, randomization has been a cornerstone of scientific experimentation, especially when dealing with humans as experimental units. In practice, however, noncompliance is
Estimation of Intervention Effects with Noncompliance: Alternative Model Specifications
This study examines alternative ways of specifying models in the complier average causal effect (CACE) estimation method, where the major interest is in estimating causal effects of treatments for
Evaluating the Effect of Training on Wages in the Presence of Noncompliance, Nonemployment, and Missing Outcome Data
TLDR
Evidence is found that the effects of a job training program, Job Corps, should have been better targeted, in the sense of being designed differently for different groups of people, and specific suggestions are offered.
Partial Identification of Local Average Treatment Effects With an Invalid Instrument
We derive nonparametric bounds for local average treatment effects (LATE) without imposing the exclusion restriction assumption or requiring an outcome with bounded support. Instead, we employ
Identification of Causal Effects Using Instrumental Variables: Comment
TLDR
It is shown that the instrumental variables (IV) estimand can be embedded within the Rubin Causal Model (RCM) and that under some simple and easily interpretable assumptions, the IV estimand is the average causal effect for a subgroup of units, the compliers.
Exploiting Multiple Outcomes in Bayesian Inference for Causal Effects with Intermediate Variables∗
In both experimental and observational studies, the causal effects of interest are often defined in terms of confounded intermediate variables, i.e., post-treatment variables potentially affected by
Identification of Causal Effects Using Instrumental Variables
TLDR
It is shown that the instrumental variables (IV) estimand can be embedded within the Rubin Causal Model (RCM) and that under some simple and easily interpretable assumptions, the IV estimand is the average causal effect for a subgroup of units, the compliers.
Exploiting multivariate outcomes in Bayesian inference for causal effects with noncompliance
A Bayesian approach to causal inference in the presence of noncompliance to assigned randomized treatment is considered. It exploits multivariate outcomes for improving estimation of weakly
Identifiability and Estimation of Causal Effects by Principal Stratification With Outcomes Truncated by Death
In medical studies, there are many situations where the final outcomes are truncated by death, in which patients die before outcomes of interest are measured. In this article we consider
...
...