A GENERAL DOUBLE ROBUSTNESS RESULT FOR ESTIMATING AVERAGE TREATMENT EFFECTS

In this paper we study doubly robust estimators of various average and quantile treatment effects under unconfoundedness; we also consider an application to a setting with an instrumental variable. We unify and extend much of the recent literature by providing a very general identification result which covers binary and multi-valued treatments; unnormalized and normalized weighting; and both inverse-probability weighted (IPW) and doubly robust estimators. We also allow for subpopulation-specific average treatment effects where subpopulations can be based on covariate values in an arbitrary way. Similar to Wooldridge (2007), we then discuss estimation of the conditional mean using quasi-log likelihoods (QLL) from the linear exponential family.

[1]  C. Rothe,et al.  Semiparametric Two-Step Estimation Using Doubly Robust Moment Conditions , 2014 .

[2]  M. Farrell.  Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations , 2013, 1309.4686.

[3]  Justin McCrary,et al.  New Evidence on the Finite Sample Properties of Propensity Score Matching and Reweighting Estimators , 2009, SSRN Electronic Journal.

[4]  J. Robins,et al.  Estimation of Regression Coefficients When Some Regressors are not Always Observed , 1994 .

[5]  Stijn Vansteelandt,et al.  Bias-Reduced Doubly Robust Estimation , 2015 .

[6]  Victor Chernozhukov,et al.  Inference on Treatment Effects after Selection Amongst High-Dimensional Controls , 2011 .

[7]  Eric J. Tchetgen Tchetgen,et al.  Alternative Identification and Inference for the Effect of Treatment on the Treated with an Instrumental Variable , 2013 .

[8]  G. Patil,et al.  Rejoinder , 2004, Environmental and Ecological Statistics.

[9]  Daniel F. McCaffrey,et al.  Comment: Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data , 2008, 0804.2962.

[10]  Alberto Abadie.  Bootstrap Tests for Distributional Treatment Effects in Instrumental Variable Models , 2002 .

[11]  Marie Davidian,et al.  Comment: Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data. , 2008, Statistical science : a review journal of the Institute of Mathematical Statistics.

[12]  S. D. Uysal.  Doubly Robust IV Estimation of Local Average Treatment Effects , 2018 .

[13]  Richard Emsley,et al.  Implementing Double-robust Estimators of Causal Effects , 2008 .

[14]  Elizabeth L. Ogburn,et al.  Doubly robust estimation of the local average treatment effect curve , 2015, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[15]  W. Newey,et al.  Large sample estimation and hypothesis testing , 1986 .

[16]  A. Belloni,et al.  Program evaluation with high-dimensional data , 2013 .

[17]  Derya Uysal.  Doubly Robust Estimation of Causal Effects with Multivalued Treatments , 2013 .

[18]  Adam Glynn,et al.  An Introduction to the Augmented Inverse Propensity Weighted Estimator , 2010, Political Analysis.

[19]  Zhiqiang Tan,et al.  Regression and Weighting Methods for Causal Inference Using Instrumental Variables , 2006 .

[20]  Qi Long,et al.  Doubly Robust Nonparametric Multiple Imputation for Ignorable Missing Data. , 2012, Statistica Sinica.

[21]  A. Belloni,et al.  Inference on Treatment Effects after Selection Amongst High-Dimensional Controls , 2011, 1201.0224.

[22]  J. Pearl.  TRYGVE HAAVELMO AND THE EMERGENCE OF CAUSAL CALCULUS , 2013, Econometric Theory.

[23]  Zhiqiang Tan,et al.  Bounded, efficient and doubly robust estimation with inverse weighting , 2010 .

[24]  Stephen G. Donald,et al.  Estimation and inference for distribution functions and quantile functions in treatment effect models , 2014 .

[25]  J. Robins,et al.  Doubly Robust Estimation in Missing Data and Causal Inference Models , 2005, Biometrics.

[26]  Quantile Treatment Effects in the Regression Discontinuity Design , 2008 .

[27]  D. Horvitz,et al.  A Generalization of Sampling Without Replacement from a Finite Universe , 1952 .

[28]  Decomposing differences in arithmetic means: a doubly robust estimation approach , 2016 .

[29]  A. Belloni,et al.  Program evaluation and causal inference with high-dimensional data , 2013, 1311.2645.

[30]  M. P. Dumont.  Comment … , 1970 .

[31]  J. Robins,et al.  Doubly Robust Estimation of a Marginal Average Effect of Treatment on the Treated With an Instrumental Variable , 2015 .

[32]  Mary S. Morgan,et al.  THE ET INTERVIEW , 1987 .

[33]  J. Wooldridge.  VIOLATING IGNORABILITY OF TREATMENT BY CONTROLLING FOR TOO MANY FACTORS , 2005, Econometric Theory.

[34]  Joseph Kang,et al.  Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data , 2007, 0804.2958.

[35]  J. Angrist,et al.  Instrumental Variables Estimates of the Effect of Subsidized Training on the Quantiles of Trainee Earnings , 1999 .

[36]  J. Robins,et al.  Comment: Performance of Double-Robust Estimators When “Inverse Probability” Weights Are Highly Variable , 2007, 0804.2965.

[37]  Tests for distributional treatment effects under unconfoundedness , 2011 .

[38]  J. Robins,et al.  Improved double-robust estimation in missing data and causal inference models. , 2012, Biometrika.

[39]  F. Peracchi,et al.  The Conditional Distribution of Excess Returns: An Empirical Analysis , 1994 .

[40]  Sergio Firpo.  Identification and Estimation of Distributional Impacts of Interventions Using Changes in Inequality Measures , 2016, SSRN Electronic Journal.

[41]  Patrick M. Kline.  Oaxaca-Blinder as a Reweighting Estimator , 2011 .

[42]  C. Cassel,et al.  Some results on generalized difference estimation and generalized regression estimation for finite populations , 1976 .

[43]  Matias D. Cattaneo,et al.  Efficient semiparametric estimation of multi-valued treatment effects under ignorability , 2010 .

[44]  M. Davidian,et al.  Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data , 2009, Biometrika.

[45]  Pedro H. C. Sant'Anna,et al.  Program Evaluation with Right-Censored Data , 2016, 1604.02642.

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

[47]  Matías Busso,et al.  Finite Sample Properties of Semiparametric Estimators of Average Treatment Effects ∗ , 2008 .

[48]  C. Rothe,et al.  Semiparametric Estimation and Inference Using Doubly Robust Moment Conditions , 2013, SSRN Electronic Journal.

[49]  B. Graham,et al.  Inverse Probability Tilting for Moment Condition Models with Missing Data , 2008 .

[50]  Myoung‐jae Lee.  Non‐parametric tests for distributional treatment effect for randomly censored responses , 2009 .

[51]  C. Gouriéroux,et al.  PSEUDO MAXIMUM LIKELIHOOD METHODS: THEORY , 1984 .

[52]  V. Chernozhukov,et al.  Inference on Counterfactual Distributions , 2009, 0904.0951.

[53]  Markus Frölich,et al.  Unconditional Quantile Treatment Effects Under Endogeneity , 2013 .

[54]  Arthur S. Goldberger,et al.  Interviewed by Nicholas M. Kiefer , 1989, Econometric Theory.

[55]  James M. Robins,et al.  On Profile Likelihood: Comment , 2000 .

[56]  Jeffrey M. Woodbridge.  Econometric Analysis of Cross Section and Panel Data , 2002 .

[57]  Zhiqiang Tan,et al.  Comment: Understanding OR, PS and DR , 2007, 0804.2969.

[58]  Zhiqiang Tan,et al.  A Distributional Approach for Causal Inference Using Propensity Scores , 2006 .

[59]  James Heckman,et al.  CAUSAL ANALYSIS AFTER HAAVELMO , 2013, Econometric Theory.

[60]  James M. Robins,et al.  Adjusting for Nonignorable Drop-Out Using Semiparametric Nonresponse Models: Rejoinder , 1999 .

[61]  David M. Drukker,et al.  Estimation of Multivalued Treatment Effects under Conditional Independence , 2013 .

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

[63]  G. Imbens.  The Role of the Propensity Score in Estimating Dose-Response Functions , 1999 .

[64]  James M. Robins,et al.  DOUBLY ROBUST INSTRUMENTAL VARIABLE REGRESSION , 2012 .

[65]  S. D. Uysal,et al.  Doubly Robust Estimation of Causal Effects with Multivalued Treatments: An Application to the Returns to Schooling , 2015 .

[66]  J. Wooldridge.  Inverse probability weighted estimation for general missing data problems , 2004 .

[67]  J. Lunceford,et al.  Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study , 2004, Statistics in medicine.

[68]  Dean Follmann,et al.  Semiparametric Double Balancing Score Estimation for Incomplete Data With Ignorable Missingness , 2012 .

[69]  G. Imbens,et al.  Estimation of Causal Effects using Propensity Score Weighting: An Application to Data on Right Heart Catheterization , 2001, Health Services and Outcomes Research Methodology.