Advertisement

Challenges to Estimating Contagion Effects from Observational Data

  • Elizabeth L. Ogburn
Chapter
Part of the Computational Social Sciences book series (CSS)

Abstract

A growing body of literature attempts to learn about contagion using observational (i.e., non-experimental) data collected from a single social network. While the conclusions of these studies may be correct, the methods rely on assumptions that are likely—and sometimes guaranteed to be—false, and therefore the evidence for the conclusions is often weaker than it seems. Developing methods that do not need to rely on implausible assumptions is an incredibly challenging and important open problem in statistics. Appropriate methods don’t (yet!) exist, so researchers hoping to learn about contagion from observational social network data are sometimes faced with a dilemma: they can abandon their research program, or they can use inappropriate methods. This chapter will focus on the challenges and the open problems and will not weigh in on that dilemma, except to mention here that the most responsible way to use any statistical method, especially when it is well-known that the assumptions on which it rests do not hold, is with a healthy dose of skepticism, with honest acknowledgment and deep understanding of the limitations, and with copious caveats about how to interpret the results.

Notes

Acknowledgement

This work was funded by the Office of Naval Research grant N00014-15-1-2343.

References

  1. 1.
    Ali MM, Dwyer DS (2009) Estimating peer effects in adolescent smoking behavior: a longitudinal analysis. J Adolesc Health 45(4):402–408Google Scholar
  2. 2.
    Angrist JD, Pischke JS (2008) Mostly harmless econometrics: an empiricist’s companion. Princeton University Press, PrincetonGoogle Scholar
  3. 3.
    Aral S, Muchnik L, Sundararajan A (2009) Distinguishing influence-based contagion from homophily-driven diffusion in dynamic networks. Proc Natl Acad Sci 106(51):21544–21549Google Scholar
  4. 4.
    Aronow PM, Samii C (2012) Estimating average causal effects under general interference. Technical reportGoogle Scholar
  5. 5.
    Besag J (1974) On spatial-temporal models and Markov fields. In: Transactions of the seventh Prague conference on information theory, statistical decision functions, and random processes. Springer, Dordrecht, pp 47–55Google Scholar
  6. 6.
    Bowers J, Fredrickson MM, Panagopoulos C (2013) Reasoning about interference between units: a general framework. Polit Anal 21(1):97–124Google Scholar
  7. 7.
    Burk WJ, Steglich CE, Snijders TA (2007) Beyond dyadic interdependence: actor-oriented models for co-evolving social networks and individual behaviors. Int J Behav Dev 31(4):397–404Google Scholar
  8. 8.
    Cacioppo JT, Fowler JH, Christakis NA (2009) Alone in the crowd: the structure and spread of loneliness in a large social network. J Pers Soc Psychol 97(6):977Google Scholar
  9. 9.
    Christakis N, Fowler J (2007) The spread of obesity in a large social network over 32 years. N Engl J Med 357(4):370–379Google Scholar
  10. 10.
    Christakis N, Fowler J (2008) The collective dynamics of smoking in a large social network. N Engl J Med 358(21):2249–2258Google Scholar
  11. 11.
    Christakis N, Fowler J (2010) Social network sensors for early detection of contagious outbreaks. PLoS One 5(9):e12948Google Scholar
  12. 12.
    Cohen-Cole E, Fletcher JM (2008) Is obesity contagious? Social networks vs. environmental factors in the obesity epidemic. J Health Econ 27(5):1382–1387Google Scholar
  13. 13.
    Elwert F, Winship C (2014) Endogenous selection bias: the problem of conditioning on a collider variable. Ann Rev Sociol 40:31–53Google Scholar
  14. 14.
    Fisher RA (1922) On the mathematical foundations of theoretical statistics. Philos Trans R Soc Lond Ser A 222:309–368. Containing papers of a mathematical or physical characterGoogle Scholar
  15. 15.
    Goetzke F (2008) Network effects in public transit use: evidence from a spatially autoregressive mode choice model for New York. Urban Stud 45(2):407–417Google Scholar
  16. 16.
    Greenland S (2000) An introduction to instrumental variables for epidemiologists. Int J Epidemiol 29(4):722–729Google Scholar
  17. 17.
    Halloran M, Hudgens M (2011) Causal inference for vaccine effects on infectiousness. The University of North Carolina at Chapel Hill Department of Biostatistics. Technical report series, p 20Google Scholar
  18. 18.
    Halloran ME, Struchiner CJ (1995) Causal inference in infectious diseases. Epidemiology 6(2):142–151Google Scholar
  19. 19.
    Hernán MA (2004) A definition of causal effect for epidemiological research. J Epidemiol Community Health 58(4):265–271Google Scholar
  20. 20.
    Hong G, Raudenbush S (2006) Evaluating kindergarten retention policy. J Am Stat Assoc 101(475):901–910Google Scholar
  21. 21.
    Hudgens M, Halloran M (2008) Toward causal inference with interference. J Am Stat Assoc 103(482):832–842Google Scholar
  22. 22.
    Kang C (2007) Classroom peer effects and academic achievement: quasi-randomization evidence from South Korea. J Urban Econ 61(3):458–495Google Scholar
  23. 23.
    Lauritzen SL, Richardson TS (2002) Chain graph models and their causal interpretations. J R Stat Soc Ser B Stat Methodol 64(3):321–348Google Scholar
  24. 24.
    Lazer D, Rubineau B, Chetkovich C, Katz N, Neblo M (2010) The coevolution of networks and political attitudes. Polit Commun 27(3):248–274Google Scholar
  25. 25.
    Lee LF (2004) Asymptotic distributions of quasi-maximum likelihood estimators for spatial autoregressive models. Econometrica 72(6):1899–1925Google Scholar
  26. 26.
    Lin X (2005) Peer effects and student academic achievement: an application of spatial autoregressive model with group unobservables. Unpublished manuscript, Ohio State UniversityGoogle Scholar
  27. 27.
    Liu L, Hudgens MG (2014) Large sample randomization inference of causal effects in the presence of interference. J Am Stat Assoc 109(505):288–301Google Scholar
  28. 28.
    Lyons R (2011) The spread of evidence-poor medicine via flawed social-network analysis. Stat Polit Policy 2(1):Article 2Google Scholar
  29. 29.
    Manski CF (1993) Identification of endogenous social effects: the reflection problem. Rev Econ Stud 60(3):531–542Google Scholar
  30. 30.
    Noel H, Nyhan B (2011) The unfriending problem: the consequences of homophily in friendship retention for causal estimates of social influence. Soc Netw 33(3):211–218Google Scholar
  31. 31.
    Ogburn EL, VanderWeele TJ (2014) Causal diagrams for interference. Stat Sci 29(4):559–578Google Scholar
  32. 32.
    Ogburn EL, VanderWeele TJ (2014) Vaccines, contagion, and social networks (preprint). arXiv:14031241Google Scholar
  33. 33.
    Ogburn EL, Volfovsky A (2016) Networks. In: Bühlmann P, Drineas P, Kane M, van der Laan MJ (eds) Handbook of big data. Chapman and Hall/CRC, Boca RatonGoogle Scholar
  34. 34.
    Ogburn EL, Sofrygin O, Diaz I, van der Laan MJ (2017, Preprint) Causal inference for social network data. arXiv:170508527Google Scholar
  35. 35.
    O’Malley JA, Marsden PV (2008) The analysis of social networks. Health Serv Outcomes Res Methodol 8(4):222–269Google Scholar
  36. 36.
    O’Malley AJ, Elwert F, Rosenquist JN, Zaslavsky AM, Christakis NA (2014) Estimating peer effects in longitudinal dyadic data using instrumental variables. Biometrics 70:506–515Google Scholar
  37. 37.
    Pearl J (2000) Causality: models, reasoning and inference. Cambridge University Press, CambridgeGoogle Scholar
  38. 38.
    Railsback SF, Grimm V (2011) Agent-based and individual-based modeling: a practical introduction. Princeton University Press, PrincetonGoogle Scholar
  39. 39.
    Rosenbaum P (2007) Interference between units in randomized experiments. J Am Stat Assoc 102(477):191–200Google Scholar
  40. 40.
    Rosenquist JN, Murabito J, Fowler JH, Christakis NA (2010) The spread of alcohol consumption behavior in a large social network. Ann Intern Med 152(7):426–433Google Scholar
  41. 41.
    Rubin D (1990) 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. Stat Sci 5(4):472–480Google Scholar
  42. 42.
    Rubin DB (2005) Causal inference using potential outcomes: design, modeling, decisions. J Am Stat Assoc 100(469):322–331Google Scholar
  43. 43.
    Sacerdote B (2000) Peer effects with random assignment: Results for Dartmouth roommates. Technical report, National Bureau of Economic ResearchGoogle Scholar
  44. 44.
    Shalizi CR (2012) Comment on “why and when ‘flawed’ social network analyses still yield valid tests of no contagion”. Stat Polit Policy 3(1). https://doi.org/10.1515/2151-7509.1053
  45. 45.
    Shalizi CR, Thomas AC (2011) Homophily and contagion are generically confounded in observational social network studies. Sociol Methods Res 40(2):211–239Google Scholar
  46. 46.
    Snijders T, Steglich C, Schweinberger M (2007) Modeling the coevolution of networks and behavior. NAGoogle Scholar
  47. 47.
    Snijders TA, Van de Bunt GG, Steglich CE (2010) Introduction to stochastic actor-based models for network dynamics. Soc Netw 32(1):44–60Google Scholar
  48. 48.
    Sobel M (2006) What do randomized studies of housing mobility demonstrate? J Am Stat Assoc 101(476):1398–1407Google Scholar
  49. 49.
    Tchetgen Tchetgen EJ, VanderWeele T (2012) On causal inference in the presence of interference. Stat Methods Med Res 21(1):55–75Google Scholar
  50. 50.
    Thomas A (2013) The social contagion hypothesis: comment on ‘social contagion theory: examining dynamic social networks and human behavior’. Stat Med 32(4):581–590Google Scholar
  51. 51.
    van der Laan MJ (2012) Causal inference for networks. UC Berkeley Division of Biostatistics, Working Paper Series, Working Paper 300Google Scholar
  52. 52.
    VanderWeele TJ (2011) Sensitivity analysis for contagion effects in social networks. Sociol Methods Res 40(2):240–255Google Scholar
  53. 53.
    VanderWeele TJ, Ogburn EL, Tchetgen EJT (2012) Statistics, politics, and policy. Polit Policy 3(1):4Google Scholar
  54. 54.
    Ver Steeg G, Galstyan A (2010) Ruling out latent homophily in social networks. In: NIPS workshop on social computingGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Johns Hopkins Bloomberg School of Public HealthBaltimoreUSA

Personalised recommendations