Causal Effects with Hidden Treatment Diffusion on Observed or Partially Observed Networks

In randomized experiments, interactions between units might generate a treatment diffusion process. This is common when the treatment of interest is an actual object or product that can be shared among peers (e.g., flyers, booklets, videos). For instance, if the intervention of interest is an information campaign realized through the distribution of a video to targeted individuals, some of these treated individuals might share the video they received with their friends. Such a phenomenon is usually unobserved, causing a misallocation of individuals in the two treatment arms: some of the initially untreated units might have actually received the treatment by diffusion. Treatment misclassification can, in turn, introduce a bias in the estimation of the causal effect. Inspired by a recent field experiment on the effect of different types of school incentives aimed at encouraging students to attend cultural events, we present a novel approach to deal with a hidden diffusion process on observed or partially observed networks. Specifically, we develop a simulation-based sensitivity analysis that assesses the robustness of the estimates against the possible presence of a treatment diffusion. We simulate several diffusion scenarios within a plausible range of sensitivity parameters and we compare the treatment effect which is estimated in each scenario with the one that is obtained while ignoring the diffusion process. Results suggest that even a treatment diffusion parameter of small size may lead to a significant bias in the estimation of the treatment effect.

[1]  Stuart Hannabuss,et al.  The International Encyclopedia of Media Effects , 2018 .

[2]  Esben Budtz-Jørgensen,et al.  Underestimation of Risk Due to Exposure Misclassification , 2005, International journal of occupational medicine and environmental health.

[3]  L. L. Doove,et al.  Recursive partitioning for missing data imputation in the presence of interaction effects , 2014, Comput. Stat. Data Anal..

[4]  Corwin M Zigler,et al.  Causal inference with interfering units for cluster and population level treatment allocation programs , 2017, Biometrics.

[5]  Esther Duflo,et al.  Do Labor Market Policies Have Displacement Effects? Evidence from a Clustered Randomized Experiment , 2012 .

[6]  A. Chin,et al.  Impact of Bilingual Education Programs on Limited English Proficient Students and Their Peers: Regression Discontinuity Evidence from Texas , 2012, SSRN Electronic Journal.

[7]  Stef van Buuren,et al.  MICE: Multivariate Imputation by Chained Equations in R , 2011 .

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

[9]  Dunia López-Pintado,et al.  Diffusion in complex social networks , 2008, Games Econ. Behav..

[10]  Danielle Braun,et al.  Using Validation Data to Adjust the Inverse Probability Weighting Estimator for Misclassified Treatment , 2016 .

[11]  Linyuan Lü,et al.  Spreading in online social networks: the role of social reinforcement. , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[13]  Jukka-Pekka Onnela,et al.  Spreading paths in partially observed social networks , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  E. Paluck,et al.  Changing climates of conflict: A social network experiment in 56 schools , 2016, Proceedings of the National Academy of Sciences.

[15]  R. Goodman,et al.  Measuring the Diffusion of Innovative Health Promotion Programs , 1992, American journal of health promotion : AJHP.

[16]  M. Rumor.  Environmental Monitoring and Assessment , 2011 .

[17]  John Bound,et al.  Measurement error in survey data , 2001 .

[18]  Jon M. Kleinberg,et al.  The link-prediction problem for social networks , 2007, J. Assoc. Inf. Sci. Technol..

[19]  Alexander Kukush,et al.  Measurement Error Models , 2011, International Encyclopedia of Statistical Science.

[20]  D. Rubin.  Multiple Imputation After 18+ Years , 1996 .

[21]  Falco J. Bargagli-Stoffi,et al.  Heterogeneous Treatment and Spillover Effects Under Clustered Network Interference , 2020, 2008.00707.

[22]  Linyuan Lu,et al.  Link Prediction in Complex Networks: A Survey , 2010, ArXiv.

[23]  Paul R. Rosenbaum,et al.  Sensitivity Analysis in Observational Studies , 2005 .

[24]  Raymond J. Carroll,et al.  Measurement error in nonlinear models: a modern perspective , 2006 .

[25]  Maya Petersen,et al.  Causal inference when counterfactuals depend on the proportion of all subjects exposed , 2017, Biometrics.

[26]  Trilochan Tripathy,et al.  Program Evaluation and Spillover Effects , 2010, SSRN Electronic Journal.

[27]  Weihua An,et al.  Causal Inference with Networked Treatment Diffusion , 2018, Sociological Methodology.

[28]  Thomas W. Valente,et al.  Diffusion of Innovations and Policy Decision‐Making , 1993 .

[29]  Fredrik Sävje,et al.  AVERAGE TREATMENT EFFECTS IN THE PRESENCE OF UNKNOWN INTERFERENCE. , 2017, Annals of statistics.

[30]  Wei Chen,et al.  Scalable influence maximization for independent cascade model in large-scale social networks , 2012, Data Mining and Knowledge Discovery.

[31]  Garry Robins,et al.  Bayesian analysis for partially observed network data, missing ties, attributes and actors , 2013, Soc. Networks.

[32]  Éva Tardos,et al.  Influential Nodes in a Diffusion Model for Social Networks , 2005, ICALP.

[33]  Laura Forastiere,et al.  Causal Inference on Networks Under Continuous Treatment Interference: An Application to Trade Distortions in Agricultural Markets , 2019, SSRN Electronic Journal.

[34]  Bruce A. Desmarais,et al.  Inferential Network Analysis with Exponential Random Graph Models , 2011, Political Analysis.

[35]  Michael P. Wellman,et al.  Modeling Information Diffusion in Networks with Unobserved Links , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[36]  Yaron Leitner.  Federal Reserve Bank of Philadelphia , 2004 .

[37]  M. Rogers,et al.  Measuring the diffusion of marketing messages across a social network , 2012 .

[38]  K. Nichol,et al.  The effectiveness of vaccination against influenza in healthy, working adults. , 1995, The New England journal of medicine.

[39]  I. Crimaldi,et al.  Modelling Network Interference with Multi-valued Treatments: the Causal Effect of Immigration Policy on Crime Rates , 2020, 2003.10525.

[40]  Prasanna Gai,et al.  Contagion in financial networks , 2010, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[41]  Wesley M. Cohen,et al.  R&D spillovers, patents and the incentives to innovate in Japan and the United States , 2002 .

[42]  Wenyaw Chan,et al.  Statistical Methods in Medical Research , 2013, Model. Assist. Stat. Appl..

[43]  P. Aronow,et al.  Design-Based Inference for Spatial Experiments with Interference , 2020 .

[44]  Els Goetghebeur,et al.  Comparison of causal effect estimators under exposure misclassification , 2010 .

[45]  D. Rubin,et al.  Assessing Sensitivity to an Unobserved Binary Covariate in an Observational Study with Binary Outcome , 1983 .

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

[47]  Danielle Braun,et al.  Adjustment for Mismeasured Exposure using Validation Data and Propensity Scores , 2014 .

[48]  J. Aislinn Bohren,et al.  Optimal Design of Experiments in the Presence of Interference , 2017, Review of Economics and Statistics.

[49]  Donald P. Green,et al.  Analysis of Cluster-Randomized Experiments: A Comparison of Alternative Estimation Approaches , 2007, Political Analysis.

[50]  E. Airoldi,et al.  Estimating Causal Effects Under Interference Using Bayesian Generalized Propensity Scores , 2018, 1807.11038.

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

[52]  Yinggang Zhou,et al.  Credit Risk Spillovers among Financial Institutions around the Global Credit Crisis: Firm-Level Evidence , 2012 .

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

[54]  Yih‐chyi Chuang,et al.  Foreign direct investment, R&D and spillover efficiency: Evidence from Taiwan's manufacturing firms , 1999 .

[55]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[56]  Ludovic Denoyer,et al.  Learning social network embeddings for predicting information diffusion , 2014, WSDM.

[57]  Robin Cowan,et al.  Network Structure and the Diffusion of Knowledge , 2004 .

[58]  J. R. Lockwood,et al.  Inverse probability weighting with error-prone covariates. , 2013, Biometrika.

[59]  Wen Wei Loh,et al.  Randomization inference with general interference and censoring , 2018, Biometrics.

[60]  Michael P. Leung.  Treatment and Spillover Effects Under Network Interference , 2019, Review of Economics and Statistics.

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

[62]  Wei Liu,et al.  Influence maximization on signed networks under independent cascade model , 2018, Applied Intelligence.

[63]  Masahiro Kimura,et al.  Prediction of Information Diffusion Probabilities for Independent Cascade Model , 2008, KES.

[64]  M. Mariani,et al.  Nudging museums attendance: a field experiment with high school teens , 2017 .

[65]  Zhichao Jiang,et al.  Causal Inference With Interference and Noncompliance in Two-Stage Randomized Experiments , 2020, Journal of the American Statistical Association.

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

[67]  Hai Jin,et al.  Scalable influence maximization under independent cascade model , 2017, J. Netw. Comput. Appl..

[68]  J. van der Laan,et al.  Sensitivity Analysis for Causal Inference Under Unmeasured Confounding and Measurement Error Problems , 2016 .

[69]  M. Mariani,et al.  Exploring Encouragement, Treatment, and Spillover Effects Using Principal Stratification, With Application to a Field Experiment on Teens’ Museum Attendance , 2021, Journal of Business & Economic Statistics.

[70]  Tyler J. VanderWeele,et al.  Opening the Blackbox of Treatment Interference: Tracing Treatment Diffusion through Network Analysis , 2019, Sociological Methods & Research.

[71]  Jian Yang,et al.  Credit Risk Spillovers among Financial Institutions around the Global Credit Crisis: Firm-Level Evidence , 2012, Manag. Sci..

[72]  Joel A. Middleton,et al.  A Class of Unbiased Estimators of the Average Treatment Effect in Randomized Experiments , 2013 .

[73]  Oleg Sofrygin,et al.  Semi-Parametric Estimation and Inference for the Mean Outcome of the Single Time-Point Intervention in a Causally Connected Population , 2016, Journal of causal inference.

[74]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

[75]  Stephen P. Borgatti,et al.  Statistical analysis of network data - an application to diffusion of innovation , 2003, Soc. Networks.

[76]  M. Meltzer,et al.  Effectiveness and cost-benefit of influenza vaccination of healthy working adults: A randomized controlled trial. , 2000, JAMA.

[77]  B. Iooss,et al.  A Review on Global Sensitivity Analysis Methods , 2014, 1404.2405.

[78]  Thomas W. Valente,et al.  Social Network Theory , 1983 .

[79]  Thomas W. Valente,et al.  Models and Methods in Social Network Analysis: Network Models and Methods for Studying the Diffusion of Innovations , 2005 .

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

[81]  Li‐Pang Chen.  Statistical analysis with measurement error or misclassification: Strategy, method and application. Grace Y. Yi. New York: Springer‐Verlag. , 2019, Biometrics.

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

[83]  G. La Torre,et al.  Diffusion of the Italian social media campaign against smoking on a social network and YouTube , 2020, Journal of preventive medicine and hygiene.

[84]  Grace Y Yi,et al.  Weighted causal inference methods with mismeasured covariates and misclassified outcomes , 2019, Statistics in medicine.

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

[86]  R. Kasprzyk.  Diffusion in Networks , 2012, Journal of Telecommunications and Information Technology.

[87]  Arthur Lewbel,et al.  Estimation of Average Treatment Effects With Misclassification , 2007 .

[88]  Peter M. Aronow,et al.  Estimating Average Causal Effects Under Interference Between Units , 2013, 1305.6156.

[89]  Damon Centola,et al.  The Spread of Behavior in an Online Social Network Experiment , 2010, Science.

[90]  F. A. Hayek.  The American Economic Review , 2007 .

[91]  D. Hamby.  A review of techniques for parameter sensitivity analysis of environmental models , 1994, Environmental monitoring and assessment.

[92]  Linyuan Lü,et al.  Predicting missing links via local information , 2009, 0901.0553.

[93]  P. Bourdieu.  Forms of Capital , 2002 .

[94]  G. Gurtner,et al.  Statistics in medicine. , 2011, Plastic and reconstructive surgery.

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

[96]  J. Carpenter,et al.  Practice of Epidemiology Comparison of Random Forest and Parametric Imputation Models for Imputing Missing Data Using MICE: A CALIBER Study , 2014 .

[97]  Elizabeth L. Ogburn,et al.  Causal Inference for Social Network Data , 2017, Journal of the American Statistical Association.

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

[99]  Tyler J Vanderweele.  Inference for additive interaction under exposure misclassification. , 2012, Biometrika.

[100]  Lena Osterhagen,et al.  Multiple Imputation For Nonresponse In Surveys , 2016 .

[101]  Duncan J. Watts,et al.  The Structural Virality of Online Diffusion , 2015, Manag. Sci..

[102]  Grace Y Yi,et al.  Causal inference with measurement error in outcomes: Bias analysis and estimation methods , 2019, Statistical methods in medical research.

[103]  P. Gertler.  Do Conditional Cash Transfers Improve Child Health? Evidence from PROGRESA’s Control Randomized Experiment. , 2004, The American economic review.

[104]  M. Sarvary,et al.  Network Effects and Personal Influences: The Diffusion of an Online Social Network , 2011 .

[105]  B. Arpino,et al.  Assessing the causal effects of financial aids to firms in Tuscany allowing for interference , 2016 .

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

[107]  J. Robins,et al.  Sensitivity Analysis for Selection bias and unmeasured Confounding in missing Data and Causal inference models , 2000 .

[108]  Takahide Yanagi.  Inference on local average treatment effects for misclassified treatment , 2018, Econometric Reviews.

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

[110]  Tyler J VanderWeele,et al.  Identification and Estimation of Causal Mechanisms in Clustered Encouragement Designs: Disentangling Bed Nets Using Bayesian Principal Stratification , 2016, Journal of the American Statistical Association.

[111]  Tao Zhou,et al.  Predicting missing links and identifying spurious links via likelihood analysis , 2016, Scientific Reports.

[112]  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.

[113]  Ian Fellows,et al.  Exponential-family Random Network Models , 2012, 1208.0121.

[114]  Teppei Yamamoto,et al.  Causal Inference with Differential Measurement Error: Nonparametric Identification and Sensitivity Analysis , 2010 .

[115]  Chia-Ling Kuo,et al.  Innovation Diffusion , 2012 .

[116]  Jon Kleinberg,et al.  The link prediction problem for social networks , 2003, CIKM '03.