A paradox from randomization-based causal inference

  title={A paradox from randomization-based causal inference},
  author={Peng Ding},
  journal={arXiv: Statistics Theory},
  • P. Ding
  • Published 2 February 2014
  • Mathematics
  • arXiv: Statistics Theory
Under the potential outcomes framework, causal effects are defined as comparisons between potential outcomes under treatment and control. To infer causal effects from randomized experiments, Neyman proposed to test the null hypothesis of zero average causal effect (Neyman's null), and Fisher proposed to test the null hypothesis of zero individual causal effect (Fisher's null). Although the subtle difference between Neyman's null and Fisher's null has caused lots of controversies and confusions… 

Figures and Tables from this paper

Exploring the Role of Randomization in Causal Inference
real data examples all support this surprising phenomenon. Besides its historical and theoretical importance, this paradox also leads to useful practical implications for modern researchers. Chapter
Stratified exact tests for the weak causal null hypothesis in randomized trials with a binary outcome
  • Y. Chiba
  • Mathematics
    Biometrical journal. Biometrische Zeitschrift
  • 2017
The stratified Fisher's exact test of Jung applies a crude estimator of the treatment effect and can be regarded as a special case of the proposed exact test.
Testing weak nulls in matched observational studies
We develop sensitivity analyses for weak nulls in matched observational studies while allowing unit-level treatment effects to vary. In contrast to randomized experiments, we show for general matched
Randomization Tests for Weak Null Hypotheses in Randomized Experiments
  • Jason WuP. Ding
  • Mathematics
    Journal of the American Statistical Association
  • 2020
Abstract The Fisher randomization test (FRT) is appropriate for any test statistic, under a sharp null hypothesis that can recover all missing potential outcomes. However, it is often sought after to
A Potential Tale of Two-by-Two Tables From Completely Randomized Experiments
Causal inference in completely randomized treatment-control studies with binary outcomes is discussed from Fisherian, Neymanian, and Bayesian perspectives, using the potential outcomes model. A
A randomization-based perspective of analysis of variance: a test statistic robust to treatment effect heterogeneity
Fisher randomization tests for Neyman's null hypothesis of no average treatment effects are considered in a finite population setting associated with completely randomized experiments with more than
Sharpening randomization-based causal inference for 22 factorial designs with binary outcomes
  • Jiannan Lu
  • Mathematics
    Statistical methods in medical research
  • 2019
The sharp lower bound of the sampling variance of the factorial effect estimator is derived, which leads to a new variance estimator that sharpens the finite-population Neymanian causal inference.
Sharp nonparametric bounds and randomization inference for treatment effects on an ordinal outcome
  • Y. Chiba
  • Mathematics
    Statistics in medicine
  • 2017
A numerical method is presented to calculate the sharp nonparametric bounds within a sample, reflecting the impact of confounding, and the use of a causal parameter for an ordinal outcome, defined as the proportion that a potential outcome under one treatment condition would not be smaller than that under the other condition.
Studentized Sensitivity Analysis for the Sample Average Treatment Effect in Paired Observational Studies
Abstract A fundamental limitation of causal inference in observational studies is that perceived evidence for an effect might instead be explained by factors not accounted for in the primary
Gaussian prepivoting for finite population causal inference
In finite population causal inference exact randomization tests can be constructed for sharp null hypotheses, hypotheses which impute the missing potential outcomes. Oftentimes inference is instead


A Potential Tale of Two-by-Two Tables From Completely Randomized Experiments
Causal inference in completely randomized treatment-control studies with binary outcomes is discussed from Fisherian, Neymanian, and Bayesian perspectives, using the potential outcomes model. A
Comments on the Neyman-Fisher Controversy and Its Consequences
The Neyman-Fisher controversy considered here originated with the 1935 presentation of Jerzy Neyman's Statistical Problems in Agricultural Experimentation to the Royal Statistical Society. Neyman
Estimating causal effects of treatments in randomized and nonrandomized studies.
A discussion of matching, randomization, random sampling, and other methods of controlling extraneous variation is presented. The objective is to specify the benefits of randomization in estimating
Causal inference from $2^k$ factorial designs using the potential outcomes model
A framework for causal inference from two-level factorial designs is proposed. The framework utilizes the concept of potential outcomes that lies at the center stage of causal inference and extends
Variance identification and efficiency analysis in randomized experiments under the matched‐pair design
  • K. Imai
  • Mathematics
    Statistics in medicine
  • 2008
This paper extends Neyman's analysis to randomized experiments under the matched-pair design where experimental units are paired based on their pre-treatment characteristics and the randomization of treatment is subsequently conducted within each matched pair.
Agnostic notes on regression adjustments to experimental data: Reexamining Freedman's critique
Freedman [Adv. in Appl. Math. 40 (2008) 180-193; Ann. Appl. Stat. 2 (2008) 176-196] critiqued ordinary least squares regression adjustment of estimated treatment effects in randomized experiments,
Mostly Harmless Econometrics: An Empiricist's Companion
The core methods in today's econometric toolkit are linear regression for statistical control, instrumental variables methods for the analysis of natural experiments, and differences-in-differences
Randomization Does Not Justify Logistic Regression
The logit model is often used to analyze experimental data. However, randomization does not justify the model, so the usual estimators can be inconsistent. A consistent estimator is proposed.
On regression adjustments to experimental data
Design of Observational Studies
Beginnings.- Dilemmas and Craftsmanship.- Causal Inference in Randomized Experiments.- Two Simple Models for Observational Studies.- Competing Theories Structure Design.- Opportunities, Devices, and