Causal Inference Using Potential Outcomes

Causal effects are defined as comparisons of potential outcomes under different treatments on a common set of units. Observed values of the potential outcomes are revealed by the assignment mechanism—a probabilistic model for the treatment each unit receives as a function of covariates and potential outcomes. Fisher made tremendous contributions to causal inference through his work on the design of randomized experiments, but the potential outcomes perspective applies to other complex experiments and nonrandomized studies as well. As noted by Kempthorne in his 1976 discussion of Savage's Fisher lecture, Fisher never bridged his work on experimental design and his work on parametric modeling, a bridge that appears nearly automatic with an appropriate view of the potential outcomes framework, where the potential outcomes and covariates are given a Bayesian distribution to complete the model specification. Also, this framework crisply separates scientific inference for causal effects and decisions based on such inference, a distinction evident in Fisher's discussion of tests of significance versus tests in an accept/reject framework. But Fisher never used the potential outcomes framework, originally proposed by Neyman in the context of randomized experiments, and as a result he provided generally flawed advice concerning the use of the analysis of covariance to adjust for posttreatment concomitants in randomized trials.

[1]  R. Fisher,et al.  On the Mathematical Foundations of Theoretical Statistics , 1922 .

[2]  Karl Pearson,et al.  On the "z" Test , 1931 .

[3]  J. Neyman.  On the Two Different Aspects of the Representative Method: the Method of Stratified Sampling and the Method of Purposive Selection , 1934 .

[4]  J. Neyman,et al.  Statistical Problems in Agricultural Experimentation , 1935 .

[5]  R Fisher,et al.  Design of Experiments , 1936 .

[6]  B. L. Welch.  ON THE z-TEST IN RANDOMIZED BLOCKS AND LATIN SQUARES , 1937 .

[7]  E. Pitman.  SIGNIFICANCE TESTS WHICH MAY BE APPLIED TO SAMPLES FROM ANY POPULATIONS III. THE ANALYSIS OF VARIANCE TEST , 1938 .

[8]  M. D. McCarthy.  On the Application of the Z-Test to Randomized Blocks , 1939 .

[9]  T. Haavelmo.  The Statistical Implications of a System of Simultaneous Equations , 1943 .

[10]  F. J. Anscombe,et al.  The Validity of Comparative Experiments , 1948 .

[11]  A. Roy.  Some thoughts on the distribution of earnings , 1951 .

[12]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[13]  M. A. Creasy.  Limits for the Ratio of Means , 1954 .

[14]  E. C. Fieller.  SOME PROBLEMS IN INTERVAL ESTIMATION , 1954 .

[15]  Frederick Mosteller,et al.  Identification and estimation. , 1955 .

[16]  R. A. Fisher,et al.  Statistical methods and scientific inference. , 1957 .

[17]  David R. Cox.  Planning of Experiments , 1958 .

[18]  R. Quandt.  The Estimation of the Parameters of a Linear Regression System Obeying Two Separate Regimes , 1958 .

[19]  Leonid Hurwicz,et al.  On the Structural Form of Interdependent Systems , 1966 .

[20]  R. Fisher.  Statistical Methods for Research Workers , 1971 .

[21]  D. Rubin.  Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[22]  D. Rubin.  INFERENCE AND MISSING DATA , 1975 .

[23]  Leonard J. Savage,et al.  On Rereading R. A. Fisher , 1976 .

[24]  Donald B. Rubin,et al.  Bayesian Inference for Causal Effects: The Role of Randomization , 1978 .

[25]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[26]  D. Basu.  Randomization Analysis of Experimental Data: The Fisher Randomization Test , 1980 .

[27]  John W. Pratt,et al.  On the nature and discovery of structure , 1981 .

[28]  D. Holt,et al.  Planning and Analysis of Observational Studies. , 1983 .

[29]  G. A. Barnard,et al.  Neyman from Life. , 1983 .

[30]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[31]  Robert Schlaifer,et al.  On the nature and discovery of structure , 1981 .

[32]  D. Rubin.  Bayesianly Justifiable and Relevant Frequency Calculations for the Applied Statistician , 1984 .

[33]  P. Holland.  Statistics and Causal Inference , 1985 .

[34]  H. Chernoff.  Sequential Analysis and Optimal Design , 1987 .

[35]  James J. Heckman,et al.  Causal Inference and Nonrandom Samples , 1989 .

[36]  J. Ware.  Investigating Therapies of Potentially Great Benefit: ECMO , 1989 .

[37]  A. Gelman,et al.  Estimating Incumbency Advantage Without Bias , 1990 .

[38]  T. Speed,et al.  On the Application of Probability Theory to Agricultural Experiments. Essay on Principles. Section 9 , 1990 .

[39]  David R. Cox,et al.  Role of Models in Statistical Analysis , 1990 .

[40]  D. Rubin.  [On the Application of Probability Theory to Agricultural Experiments. Essay on Principles. Section 9.] Comment: Neyman (1923) and Causal Inference in Experiments and Observational Studies , 1990 .

[41]  B. Efron,et al.  Compliance as an Explanatory Variable in Clinical Trials , 1991 .

[42]  J. Angrist,et al.  Identification and Estimation of Local Average Treatment Effects , 1995 .

[43]  Rory A. Fisher,et al.  The Arrangement of Field Experiments , 1992 .

[44]  Joshua D. Angrist,et al.  Identification of Causal Effects Using Instrumental Variables , 1993 .

[45]  J. Angrist,et al.  Identification and Estimation of Local Average Treatment Effects , 1994 .

[46]  Xiao-Li Meng,et al.  Posterior Predictive $p$-Values , 1994 .

[47]  D. Rubin,et al.  Intention‐to‐treat analysis and the goals of clinical trials , 1995, Clinical pharmacology and therapeutics.

[48]  Judea Pearl,et al.  CAUSATION, ACTION, AND COUNTERFACTUALS , 2004 .

[49]  Xiao-Li Meng,et al.  POSTERIOR PREDICTIVE ASSESSMENT OF MODEL FITNESS VIA REALIZED DISCREPANCIES , 1996 .

[50]  James J. Heckman,et al.  Identification of Causal Effects Using Instrumental Variables: Comment , 1996 .

[51]  JoAnn E. Manson,et al.  Design of the Women's Health Initiative clinical trial and observational study. The Women's Health Initiative Study Group. , 1998, Controlled clinical trials.

[52]  Christopher Winship,et al.  THE ESTIMATION OF CAUSAL EFFECTS FROM OBSERVATIONAL DATA , 1999 .

[53]  J. Pearl,et al.  Causal diagrams for epidemiologic research. , 1999, Epidemiology.

[54]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[55]  A. P. Dawid,et al.  Causal inference without counterfactuals (with Discussion) , 2000 .

[56]  R J Little,et al.  Causal effects in clinical and epidemiological studies via potential outcomes: concepts and analytical approaches. , 2000, Annual review of public health.

[57]  A. Dawid.  Causal Inference without Counterfactuals , 2000 .

[58]  S G Baker,et al.  Compliance Subsampling Designs for Comparative Research: Estimation and Optimal Planning , 2001, Biometrics.

[59]  D. Rubin,et al.  Principal Stratification in Causal Inference , 2002, Biometrics.

[60]  Xiao-Hua Zhou,et al.  Clustered encouragement designs with individual noncompliance: bayesian inference with randomization, and application to advance directive forms. , 2002, Biostatistics.

[61]  J. Manson,et al.  Understanding the divergent data on postmenopausal hormone therapy. , 2003, The New England journal of medicine.

[62]  D. Rubin.  Direct and Indirect Causal Effects via Potential Outcomes * , 2004 .

[63]  M. Lechner,et al.  Identification of the effects of dynamic treatments by sequential conditional independence assumptions , 2005 .

[64]  M. Lechner.  A Note on Endogenous Control Variables in Evaluation Studies , 2005 .

[65]  Donald B. Rubin,et al.  Matched Sampling for Causal Effects: William G. Cochran's Contributions to the Design, Analysis, and Evaluation of Observational Studies , 2006 .

[66]  M. Lechner.  The Relation of Different Concepts of Causality in Econometrics , 2006 .