Combining Double Sampling and Bounds to Address Nonignorable Missing Outcomes in Randomized Experiments
Bibliographic Data
| ID | 6332282 |
|---|---|
| Authors | Alexander Coppock (0000-0002-5733-2386, Yale University), Alan S Gerber (0000-0002-8133-3995, Yale University), Donald P Green (0000-0002-8850-438X, Columbia University), Holger L Kern, Holger Kern (Florida State University, corresponding author) |
| Year | 2017 |
| Volume | 25 |
| Issue | 2 |
| Pages | 188-206 |
| Publication date | 2017-04-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Political Analysis (JOURNAL) |
| Journal identifiers | ISSN: 1047-1987 • E-ISSN: 1476-4989 |
| Publisher | Cambridge University Press (CUP) (PUBLISHER) |
| DOI | 10.1017/pan.2016.6 |
| OpenAlex | W3124452238 |
| Language | EN |
| Citations received | 8 |
| References cited | 48 |
Missing outcome data plague many randomized experiments. Common solutions rely on ignorability assumptions that may not be credible in all applications. We propose a method for confronting missing outcome data that makes fairly weak assumptions but can still yield informative bounds on the average treatment effect. Our approach is based on a combination of the double sampling design and nonparametric worst-case bounds. We derive a worst-case bounds estimator under double sampling and provide analytic expressions for variance estimators and confidence intervals. We also propose a method for covariate adjustment using poststratification and a sensitivity analysis for nonignorable missingness. Finally, we illustrate the utility of our approach using Monte Carlo simulations and a placebo-controlled randomized field experiment on the effects of persuasion on social attitudes with survey-based outcome measures
Average treatment effect · Confidence interval · Covariate · Econometrics · Estimator · Missing data · Nonparametric statistics · Outcome (game theory · Randomized experiment · Randomized response · Sampling (signal processing · Statistics · Variance (accounting · Advanced Causal Inference Techniques · Computer Science · Mathematics · Statistical Methods and Bayesian Inference · Survey Sampling and Estimation Techniques
A Practical Guide to Dealing with Attrition in Political Science Experiments
Countering Non-Ignorable Nonresponse in Survey Models with Randomized Response Instruments and Doubly Robust Estimation
How Conditioning on Posttreatment Variables Can Ruin Your Experiment and What to Do about It
Estimating the causal effects of cognitive effort and policy information on party cue influence
Reducing attrition in phone-based panel surveys
Identifying Media Effects Through Low-Cost, Multiwave Field Experiments
Combining Double Sampling and Bounds to Address Nonignorable Missing Outcomes in Randomized Experiments
Phantom Counterfactuals
Statistical analysis with missing data
Causal Inference for Statistics, Social, and Biomedical Sciences
Observational Studies
Assessing Sensitivity to an Unobserved Binary Covariate in an Observational Study with Binary Outcome
Training, Wages, and Sample Selection
Misunderstandings Between Experimentalists and Observationalists about Causal Inference
Demystifying Double Robustness
Confidence Intervals for Partially Identified Parameters
Sample Selection Bias as a Specification Error
Identification Problems in the Social Sciences
Bounding Disagreements about Treatment Effects
Does Media Coverage of Partisan Polarization Affect Political Attitudes
Endogeneity in Probit Response Models
Combining Double Sampling and Bounds to Address Nonignorable Missing Outcomes in Randomized Experiments
Semi-parametric Selection Models for Potentially Non-ignorable Attrition in Panel Studies with Refreshment Samples
How Much Is Minnesota Like Wisconsin? Assumptions and Counterfactuals in Causal Inference with Observational Data
Looking Beyond Demographics
Causal Inference without Ignorability
Baseline, Placebo, and Treatment
| Citations per year | 0.89 |
|---|---|
| Citation span | 2017 - 2026 (10) |
| Highly cited | No |