Health Services and Outcomes Research Methodology

, Volume 12, Issue 4, pp 237–253 | Cite as

Near/far matching: a study design approach to instrumental variables

  • Mike Baiocchi
  • Dylan S. Small
  • Lin Yang
  • Daniel Polsky
  • Peter W. Groeneveld


Classic instrumental variable techniques involve the use of structural equation modeling or other forms of parameterized modeling. In this paper we use a nonparametric, matching-based instrumental variable methodology that is based on a study design approach. Similar to propensity score matching, though unlike classic instrumental variable approaches, near/far matching is capable of estimating causal effects when the outcome is not continuous. Unlike propensity score matching, though similar to instrumental variable techniques, near/far matching is also capable of estimating causal effects even when unmeasured covariates produce selection bias. We illustrate near/far matching by using Medicare data to compare the effectiveness of carotid arterial stents with cerebral protection versus carotid endarterectomy for the treatment of carotid stenosis.


Instrumental variables Matching Study design Binary outcomes Comparative effectiveness Medicare data 



Grant support by National Heart, Lung, and Blood Institute R01HL086919, Agency for Healthcare Research and Quality R01HS018403, National Science Foundation SES 0961971.


  1. Angrist, J.: Estimation of limited dependent variable models with dummy endogenous regressors: simple strategies for empirical practice. JBES 19, 2–16 (2001)Google Scholar
  2. Angrist, J.D., Imbens, G.W., Rubin, D.: Identification of causal effects using instrumental variables (with Discussion). J. Am. Stat. Assoc. 91, 444–455 (1996)CrossRefGoogle Scholar
  3. Angrist, J., Pischke, J.: Mostly Harmless Econometrics. Princeton University Press, Princeton (2009)Google Scholar
  4. Avriel, M.: Nonlinear Programming. Prentice Hall, New Jersey (1976)Google Scholar
  5. Baiocchi, M., Small, D., Lorch, S., Rosenbaum, P.: Building a stronger instrument in an observational study of perinatal care for premature infants. J. Am. Stat. Assoc. 105, 1285–1296 (2010)CrossRefGoogle Scholar
  6. Barnett, H.J., Eliasziw, M., Meldrum, H.E., Taylor, D.W.: Do the facts and figures warrant a 10-fold increase in the performance of carotid endarterectomy on asymptomatic patients? Neurology 46(3), 603–608 (1996)PubMedCrossRefGoogle Scholar
  7. Bhattacharya, J., Goldman, D., McCaffrey, D.: Estimating probit models with self-selected treatments. Stat. Med. 25, 389–413 (2006)Google Scholar
  8. Bound, J., Jaeger, D.A., Baker, R.M.: Problems with instrumental variables estimation when the correlation between the instruments and the endogenous explanatory variable is weak. J. Am. Stat. Assoc. 90, 443–450 (1995)Google Scholar
  9. Cai, B., Small, D., Ten Have, T.: Two-stage instrumental variable methods for estimating the causal odds ratio: analysis of bias. Stat. Med. 30, 1809–1824 (2011)PubMedCrossRefGoogle Scholar
  10. Derigs, U.: Solving nonbipartite matching problems by shortest path techniques. Ann. Oper. Res. 13, 225–261 (1988)CrossRefGoogle Scholar
  11. Dodick, D.W., Meissner, I., Meyer, F.B., Cloft, H.J.: Evaluation and management of asymptomatic carotid artery stenosis. Mayo Clin. Proc. 79(7), 937–944 (2004)PubMedCrossRefGoogle Scholar
  12. Hansen, B.B., Klopfer, S.O.: Optimal full matching and related designs via network flows. JCGS 1988(15), 609–627 (2006)Google Scholar
  13. Holland, P.W.: Causal inference, path analysis, and recursive structural equations models. In: Clogg, C.C. (ed.) Sociological Methodology, vol 18, pp. 449–484. American Sociological Association, Washington, DC (1986)Google Scholar
  14. Imbens, G.W.: Sensitivity to exogeneity assumptions in program evaluation. Am. Econ. Rev. 93, 126–132 (2003)CrossRefGoogle Scholar
  15. Lu, B.: Propensity score matching with time-dependent covariates. Biometrics 61, 721–728 (2005)Google Scholar
  16. Lu, B., Rosenbaum, P.R.: Optimal matching with two control groups. J. Comput. Graph. Stat. 13, 422–434 (2004)Google Scholar
  17. Lu, B., Zanutto, E., Hornik, R., Rosenbaum, P.R.: Matching with doses in an observational study of a media campaign against drug abuse. J. Am. Stat. Assoc. 96, 1245–1253 (2001)CrossRefGoogle Scholar
  18. Mas, J.L., Chatellier, G., Beyssen, B., Branchereau, A., Moulin, T., Becquemin, J.P., et al.: Endarterectomy versus stenting in patients with symptomatic severe carotid stenosis. N. Engl. J. Med. 355(16), 1660–1671 (2006)PubMedCrossRefGoogle Scholar
  19. Mas, J.L., Trinquart, L., Leys, D., Albucher, J.F., Rousseau, H., Viguier, A., et al.: Endarterectomy versus angioplasty in patients with symptomatic severe carotid stenosis (EVA-3S) trial: results up to 4 years from a randomised, multicentre trial. Lancet Neurol. 7(10), 885–892 (2008)PubMedCrossRefGoogle Scholar
  20. Neyman, J.: On the application of probability theory to agricultural experiments. Stat. Sci. 5, 463–480 (1923, 1990)Google Scholar
  21. Robins, J.M., Rotnitzky, A., Scharfstein, D.: Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference. In: Halloran, E., Berry, D. (eds.) Statistical Models in Epidemiology, pp. 1–94. Springer, New York (1999)Google Scholar
  22. Rosenbaum, P.: The consequences of adjustment for a concomitant variable that has been affected by the treatment. J. R. Stat. Soc. Ser. A 147(5), 656–666 (1984)CrossRefGoogle Scholar
  23. Rosenbaum, P.R.: Observational Studies, 2nd edn. Springer, New York (2002)Google Scholar
  24. Rosenbaum, P.R.: An exact, distribution free test comparing two multivariate distributions based on adjacency. J. R. Stat. Soc. B 67, 515–530 (2005)Google Scholar
  25. Rosenbaum, P.R.: Design of Observational Studies. Springer, New York (2010)CrossRefGoogle Scholar
  26. Rosenbaum, P.R., Rubin, D.B.: The central role of the propensity score in observational studies for causal effects. Biometrika 70, 41–55 (1983)CrossRefGoogle Scholar
  27. Rubin, D.B.: Estimating causal effects of treatments in randomized and nonrandomized studies. J. Educ. Psychol. 66, 688–701 (1974)Google Scholar
  28. Small, D.: Sensitivity analysis for instrumental variables regression with overidentifying restrictions. J. Am. Stat. Assoc. 102, 1049–1058 (2007)Google Scholar
  29. Terza, J., Basu, A., Rathouz, P.: Two-stage residual inclusion estimation: addressing endogeneity in health econometric modeling. J. Health Econ. 27(3), 531–543 (2008)PubMedCrossRefGoogle Scholar
  30. Yadav, J.S., Wholey, M.H., Kuntz, R.E., Fayad, P., Katzen, B.T., Mishkel, G.J., et al.: Protected carotid-artery stenting versus endarterectomy in high-risk patients. N. Engl. J. Med. 351(15), 1493–1501 (2004)PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Mike Baiocchi
    • 1
  • Dylan S. Small
    • 4
    • 5
  • Lin Yang
    • 3
  • Daniel Polsky
    • 3
    • 4
  • Peter W. Groeneveld
    • 2
    • 3
    • 4
  1. 1.Department of StatisticsStanford UniversityStanfordUSA
  2. 2.Department of Veterans Affairs’ Center for Health Equity Research and PromotionPhiladelphia Veterans Affairs Medical CenterPhiladelphiaUSA
  3. 3.Department of MedicineUniversity of Pennsylvania School of MedicinePhiladelphiaUSA
  4. 4.Leonard Davis Institute of Health EconomicsUniversity of PennsylvaniaPhiladelphiaUSA
  5. 5.Department of StatisticsThe Wharton School, University of PennsylvaniaPhiladelphiaUSA

Personalised recommendations