Auto-G-Computation of Causal Effects on a Network

Methods for inferring average causal effects have traditionally relied on two key assumptions: (i) the intervention received by one unit cannot causally influence the outcome of another; and (ii) units can be organized into non-overlapping groups such that outcomes of units in separate groups are independent. In this paper, we develop new statistical methods for causal inference based on a single realization of a network of connected units for which neither assumption (i) nor (ii) holds. The proposed approach allows both for arbitrary forms of interference, whereby the outcome of a unit may depend on interventions received by other units with whom a network path through connected units exists; and long range dependence, whereby outcomes for any two units likewise connected by a path in the network may be dependent. Under network versions of consistency and no unobserved confounding, inference is made tractable by an assumption that the network's outcome, treatment and covariate vectors are a single realization of a certain chain graph model. This assumption allows inferences about various network causal effects via the auto-g-computation algorithm, a network generalization of Robins' well-known g-computation algorithm previously described for causal inference under assumptions (i) and (ii).

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

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

[3]  R. L. Brooks On colouring the nodes of a network , 1941, Mathematical Proceedings of the Cambridge Philosophical Society.

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

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

[6]  J. Zenilman,et al.  Relative prevalence of different sexually transmitted infections in HIV-discordant sexual partnerships: data from a risk network study in a high-risk New York neighbourhood , 2007, Sexually Transmitted Infections.

[7]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[8]  Bianca L. De Stavola,et al.  Gformula: Estimating Causal Effects in the Presence of Time-Varying Confounding or Mediation using the G-Computation Formula , 2011 .

[9]  Fabrizio Grandoni,et al.  A measure & conquer approach for the analysis of exact algorithms , 2009, JACM.

[10]  Elizabeth L. Ogburn,et al.  Causal diagrams for interference , 2014, 1403.1239.

[11]  Kelly Quinn,et al.  Dissolution of Committed Partnerships during Incarceration and STI/HIV-Related Sexual Risk Behavior after Prison Release among African American Men , 2018, Journal of Urban Health.

[12]  Jun S. Liu,et al.  Monte Carlo strategies in scientific computing , 2001 .

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

[14]  Uwe Siebert,et al.  Effects of multiple interventions , 2004 .

[15]  Tim Hesterberg,et al.  Monte Carlo Strategies in Scientific Computing , 2002, Technometrics.

[16]  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.

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

[18]  Eric J Tchetgen Tchetgen,et al.  Interference and Sensitivity Analysis. , 2014, Statistical science : a review journal of the Institute of Mathematical Statistics.

[19]  J. Robins A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

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

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

[22]  R. L. Brooks On Colouring the Nodes of a Network , 1941 .

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

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

[25]  Kazuhisa Makino,et al.  New Algorithms for Enumerating All Maximal Cliques , 2004, SWAT.

[26]  M. Hudgens,et al.  Assessing effects of cholera vaccination in the presence of interference , 2014, Biometrics.

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

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

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

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

[31]  John Michael Robson,et al.  Algorithms for Maximum Independent Sets , 1986, J. Algorithms.

[32]  Natalya Verbitsky-Savitz,et al.  Causal Inference Under Interference in Spatial Settings: A Case Study Evaluating Community Policing Program in Chicago , 2012 .

[33]  Jessica G. Young,et al.  The parametric g‐formula to estimate the effect of highly active antiretroviral therapy on incident AIDS or death , 2012, Statistics in medicine.

[34]  Ilya Shpitser,et al.  Modeling Interference Via Symmetric Treatment Decomposition , 2017, 1709.01050.

[35]  Victor J. Schoenbach,et al.  Incarceration and High-Risk Sex Partnerships among Men in the United States , 2009, Journal of Urban Health.

[36]  Eric D. Kolaczyk,et al.  Statistical Analysis of Network Data: Methods and Models , 2009 .

[37]  David Zuckerman,et al.  Electronic Colloquium on Computational Complexity, Report No. 100 (2005) Linear Degree Extractors and the Inapproximability of MAX CLIQUE and CHROMATIC NUMBER , 2005 .

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

[39]  T. VanderWeele,et al.  Components of the indirect effect in vaccine trials: identification of contagion and infectiousness effects. , 2012, Epidemiology.

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

[41]  J. Besag Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

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

[43]  Michael I. Jordan Graphical Models , 2003 .

[44]  Mathias Lundin,et al.  Estimation of causal effects in observational studies with interference between units , 2014, Stat. Methods Appl..

[45]  Mark J. van der Laan,et al.  Causal Inference for a Population of Causally Connected Units , 2014 .

[46]  J. Robins,et al.  Intervening on risk factors for coronary heart disease: an application of the parametric g-formula. , 2009, International journal of epidemiology.

[47]  Bianca L. De Stavola,et al.  Gformula: Estimating Causal Effects in the Presence of Time-Varying Confounding or Mediation using the G-Computation Formula , 2011 .

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

[49]  J. M. Hammersley,et al.  Markov fields on finite graphs and lattices , 1971 .

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

[51]  L. Baxter Random Fields on a Network: Modeling, Statistics, and Applications , 1996 .

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

[53]  Klaus Nordhausen,et al.  Statistical Analysis of Network Data with R , 2015 .

[54]  Magnús M. Halldórsson,et al.  Algorithm Theory - SWAT 2000 , 2000 .

[55]  Grégory Jolivet,et al.  Evidence of Treatment Spillovers Within Markets , 2014, Review of Economics and Statistics.

[56]  J. Lawson Comparative Quantification of Health Risks. Global and Regional Burden of Disease Attributable to Selected Major Risk Factors , 2006 .

[57]  T. Richardson Single World Intervention Graphs ( SWIGs ) : A Unification of the Counterfactual and Graphical Approaches to Causality , 2013 .

[58]  Judea Pearl,et al.  Causal Inference , 2010 .

[59]  Eric D. Kolaczyk,et al.  Statistical Analysis of Network Data with R , 2020, Use R!.

[60]  S. Raudenbush,et al.  Evaluating Kindergarten Retention Policy , 2006 .