AVERAGE TREATMENT EFFECTS IN THE PRESENCE OF UNKNOWN INTERFERENCE.

We investigate large-sample properties of treatment effect estimators under unknown interference in randomized experiments. The inferential target is a generalization of the average treatment effect estimand that marginalizes over potential spillover effects. We show that estimators commonly used to estimate treatment effects under no interference are consistent for the generalized estimand for several common experimental designs under limited but otherwise arbitrary and unknown interference. The rates of convergence depend on the rate at which the amount of interference grows and the degree to which it aligns with dependencies in treatment assignment. Importantly for practitioners, the results imply that if one erroneously assumes that units do not interfere in a setting with limited, or even moderate, interference, standard estimators are nevertheless likely to be close to an average treatment effect if the sample is sufficiently large. Conventional confidence statements may, however, not be accurate.

[1]  Dean Eckles,et al.  Design and Analysis of Experiments in Networks: Reducing Bias from Interference , 2014, ArXiv.

[2]  M. Hudgens,et al.  Toward Causal Inference With Interference , 2008, Journal of the American Statistical Association.

[3]  Tyler J. VanderWeele,et al.  Vaccines, Contagion, and Social Networks , 2014, ArXiv.

[4]  Béla Bollobás,et al.  Random Graphs , 1985 .

[5]  Bernard Fortin,et al.  Identification of Peer Effects through Social Networks , 2007, SSRN Electronic Journal.

[6]  C. T. Isaki,et al.  Survey Design under the Regression Superpopulation Model , 1982 .

[7]  Stephen R Cole,et al.  The consistency statement in causal inference: a definition or an assumption? , 2009, Epidemiology.

[8]  Alex J. Chin,et al.  Central limit theorems via Stein's method for randomized experiments under interference , 2018, 1804.03105.

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

[10]  G. Imbens,et al.  Exact p-Values for Network Interference , 2015, 1506.02084.

[11]  Edoardo M. Airoldi,et al.  Identification and Estimation of Treatment and Interference Effects in Observational Studies on Networks , 2016, Journal of the American Statistical Association.

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

[13]  Michael G. Hudgens,et al.  Large Sample Randomization Inference of Causal Effects in the Presence of Interference , 2014, Journal of the American Statistical Association.

[14]  Ravi Jagadeesan,et al.  Designs for estimating the treatment effect in networks with interference , 2017, The Annals of Statistics.

[15]  Avi Feller,et al.  Exact tests for two-stage randomized designs in the presence of interference , 2017 .

[16]  G. Imbens,et al.  Social Networks and the Identification of Peer Effects , 2013 .

[17]  C. Manski.  Identification of Endogenous Social Effects: The Reflection Problem , 1993 .

[18]  J. Angrist,et al.  The Perils of Peer Effects , 2013 .

[19]  M. Elizabeth Halloran,et al.  Dependent Happenings: a Recent Methodological Review , 2016, Current Epidemiology Reports.

[20]  G. Imbens,et al.  Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score , 2000 .

[21]  Walter Philipp,et al.  The central limit problem for mixing sequences of random variables , 1969 .

[22]  D. Sussman,et al.  Elements of estimation theory for causal effects in the presence of network interference , 2017, 1702.03578.

[23]  Guillaume W. Basse,et al.  Randomization tests of causal effects under interference , 2019, Biometrika.

[24]  Jon M. Kleinberg,et al.  Graph cluster randomization: network exposure to multiple universes , 2013, KDD.

[25]  Yu. A. Davydov,et al.  The Invariance Principle for Stationary Processes , 1970 .

[26]  Forrest W. Crawford,et al.  Randomization for the direct effect of an infectious disease intervention in a clustered study population , 2018 .

[27]  David W. Nickerson.  Is Voting Contagious? Evidence from Two Field Experiments , 2008, American Political Science Review.

[28]  D. A. Edwards.  On the Kantorovich–Rubinstein theorem , 2011 .

[29]  M. Hudgens,et al.  Exact Confidence Intervals in the Presence of Interference. , 2015, Statistics & probability letters.

[30]  Alan M. Frieze,et al.  Random graphs , 2006, SODA '06.

[31]  Louis H. Y. Chen,et al.  Normal approximation under local dependence , 2004, math/0410104.

[32]  Dylan S. Small,et al.  Inference With Interference Between Units in an fMRI Experiment of Motor Inhibition , 2011, Journal of the American Statistical Association.

[33]  D. Rubin,et al.  Causal Inference for Statistics, Social, and Biomedical Sciences: Causality: The Basic Framework , 2015 .

[34]  T. VanderWeele,et al.  Effect partitioning under interference in two-stage randomized vaccine trials. , 2011, Statistics & probability letters.

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

[36]  P. Rosenbaum.  Interference Between Units in Randomized Experiments , 2007 .

[37]  J. Heckman,et al.  Econometric Causality , 2008 .

[38]  Edoardo Airoldi,et al.  Limitations of Design-based Causal Inference and A/B Testing under Arbitrary and Network Interference , 2017, Sociological Methodology.

[39]  Donald P. Green,et al.  Detecting Spillover Effects: Design and Analysis of Multilevel Experiments , 2012 .

[40]  W. Lin,et al.  Agnostic notes on regression adjustments to experimental data: Reexamining Freedman's critique , 2012, 1208.2301.

[41]  P. Aronow,et al.  Research Note: A More Powerful Test Statistic for Reasoning about Interference between Units , 2016, Political Analysis.

[42]  Jake Bowers,et al.  Reasoning about Interference Between Units: A General Framework , 2013, Political Analysis.

[43]  Naoki Egami.  Unbiased Estimation and Sensitivity Analysis for Network-Specific Spillover Effects: Application to An Online Network Experiment , 2017 .

[44]  M. Halloran,et al.  Causal Inference in Infectious Diseases , 1995, Epidemiology.

[45]  Edoardo M. Airoldi,et al.  Model-assisted design of experiments in the presence of network-correlated outcomes , 2015, Biometrika.

[46]  D. Basu,et al.  An Essay on the Logical Foundations of Survey Sampling, Part One* , 2011 .

[47]  D. V. Lindley,et al.  Randomization Analysis of Experimental Data: The Fisher Randomization Test Comment , 1980 .

[48]  Peter M. Aronow,et al.  Estimating Average Causal Effects Under General Interference , 2012 .

[49]  Michael E. Sobel,et al.  What Do Randomized Studies of Housing Mobility Demonstrate? , 2006 .

[50]  P. Robinson,et al.  On the Convergence of the Horvitz‐Thompson Estimator , 1982 .

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

[52]  G. Imbens,et al.  Peer Encouragement Designs in Causal Inference with Partial Interference and Identification of Local Average Network Effects , 2016, 1609.04464.

[53]  D. L. Hanson,et al.  On the strong law of large numbers for a class of stochastic processes , 1963 .

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

[55]  Raj Chetty,et al.  Sufficient Statistics for Welfare Analysis : A Bridge Between Structural and Reduced-Form Methods , 2009 .

[56]  J. Robins,et al.  Estimating causal effects from epidemiological data , 2006, Journal of Epidemiology and Community Health.

[57]  Eric J. Tchetgen Tchetgen,et al.  Auto-G-Computation of Causal Effects on a Network , 2017, Journal of the American Statistical Association.

[58]  P. Aronow.  A General Method for Detecting Interference Between Units in Randomized Experiments , 2010 .

[59]  Tyler J VanderWeele,et al.  On causal inference in the presence of interference , 2012, Statistical methods in medical research.

[60]  J. Hahn.  On the Role of the Propensity Score in Efficient Semiparametric Estimation of Average Treatment Effects , 1998 .

[61]  David S. Choi,et al.  Estimation of Monotone Treatment Effects in Network Experiments , 2014, ArXiv.

[62]  M. Hudgens,et al.  On inverse probability-weighted estimators in the presence of interference , 2016, Biometrika.

[63]  Lung-fei Lee,et al.  Identification and estimation of econometric models with group interactions, contextual factors and fixed effects , 2007 .

[64]  G. Imbens,et al.  Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score , 2002 .

[65]  M. Rosenblatt.  A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION. , 1956, Proceedings of the National Academy of Sciences of the United States of America.

[66]  Colin B. Fogarty.  On mitigating the analytical limitations of finely stratified experiments , 2017, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[67]  D. Rubin,et al.  Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction , 2016 .

[68]  Charles F. Manski,et al.  Identification of Treatment Response with Social Interactions , 2013 .

[69]  I NICOLETTI,et al.  The Planning of Experiments , 1936, Rivista di clinica pediatrica.

[70]  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 .

[71]  Avi Feller,et al.  Analyzing Two-Stage Experiments in the Presence of Interference , 2016, 1608.06805.

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

[73]  D. Green,et al.  Get Out the Vote!: How to Increase Voter Turnout , 2004 .

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

[75]  Bryan S. Graham,et al.  Identifying Social Interactions Through Conditional Variance Restrictions , 2008 .

[76]  P. Aronow,et al.  Confidence intervals for linear unbiased estimators under constrained dependence , 2018 .

[77]  Edward K. Kao,et al.  Estimation of Causal Peer Influence Effects , 2013, ICML.