Advertisement

Instrumental Variable Analysis

  • Michael BaiocchiEmail author
  • Jing Cheng
  • Dylan S. Small
Reference work entry
Part of the Health Services Research book series (HEALTHSR)

Abstract

A goal of many health services research studies is to determine the causal effect of a treatment or intervention on health outcomes. Often, it is not ethically or practically possible to conduct a perfectly randomized experiment, and instead an observational study must be used. A major difficulty with observational studies is that there might be unmeasured confounding, i.e., unmeasured ways in which the treatment and control groups differ before treatment that affect the outcome. Instrumental variable analysis is a method for controlling for unmeasured confounding. Instrumental variable analysis requires the measurement of a valid instrumental variable, which is a variable that is independent of the unmeasured confounding and encourages a subject to take one treatment level versus another, while having no effect on the outcome beyond its encouragement of a certain treatment level. This chapter discusses the types of causal effects that can be estimated by instrumental variable analysis, the assumptions needed for instrumental variable analysis to provide valid estimates of causal effects and sensitivity analysis for those assumptions, methods of estimation of causal effects using instrumental variables, and sources of instrumental variables in health services research studies.

Notes

Acknowledgments

Jing Cheng and Dylan Small were supported by grant RC4MH092722 from the National Institute of Mental Health. The authors thank Scott Lorch for the use of the data from the NICU study.

References

  1. Abadie A. Bootstrap tests for distributional treatment effects in instrumental variable models. J Am Stat Assoc. 2002;97:284–92.CrossRefGoogle Scholar
  2. Abadie A. Semiparametric instrumental variable estimation of treatment response models. J Econ. 2003;113:231–63.CrossRefGoogle Scholar
  3. Aidoo M, Terlouw D, Kolczak M, McElroy P, ter Kuile F, Kariuki S, Nahlen B, Lal A, Udhayakumar V. Protective effects of the sickle cell gene against malaria morbidity and mortality. Lancet. 2002;359:1311–2.PubMedCrossRefGoogle Scholar
  4. Anderson J. Multivariate logistic compounds. Biometrika. 1979;66:17–26.CrossRefGoogle Scholar
  5. Angrist J. Estimation of limited dependent variable models with dummy endogenous regressors. J Bus Econ Stat. 2001;19:2–28.CrossRefGoogle Scholar
  6. Angrist J, Imbens G. Two-stage least squares estimation of average causal effects in models with variable treatment intensity. J Am Stat Assoc. 1995;90:430–42.CrossRefGoogle Scholar
  7. Angrist J, Krueger A. Does compulsory school attendance affect schooling and earnings? Q J Econ. 1991;106:979–1014.CrossRefGoogle Scholar
  8. Angrist J, Krueger A. The effect of age at school entry on educational attainment: an application of instrumental variables with moments from two samples. J Am Stat Assoc. 1992;87:328–36.CrossRefGoogle Scholar
  9. Angrist J, Krueger A. Why do World War II veterans earn more than nonveterans? J Labor Econ. 1994;12:74–97.CrossRefGoogle Scholar
  10. Angrist J, Pischke J-S. Mostly harmless econometrics: an empiricist’s companion. Princeton/Oxford: Princeton University Press; 2009.Google Scholar
  11. Angrist J, Imbens G, Rubin D. Identification of causal effects using instrumental variables. J Am Stat Assoc. 1996;91:444–55.CrossRefGoogle Scholar
  12. 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. 2010;105:1285–96.CrossRefGoogle Scholar
  13. Baiocchi M, Small D, Yang L, Polsky D, Groeneveld P. Near/far matching: a study design approach to instrumental variables. Health Serv Outcome Res Methodol. 2012;12:237–53.CrossRefGoogle Scholar
  14. Baker S. Analysis of survival data from a randomized trial with all-or-none compliance: estimating the cost-effectiveness of a cancer screening program. J Am Stat Assoc. 1998;93:929–34.CrossRefGoogle Scholar
  15. Balke A, Pearl J. Bounds on treatment effects for studies with imperfect compliance. J Am Stat Assoc. 1997;92:1171–6.CrossRefGoogle Scholar
  16. Basu A, Heckman J, Navarro-Lozano S, Urzua S. Use of instrumental variables in the presence of heterogeneity and self-selection: an application to treatments of breast cancer patients. Health Econ. 2007;16:1133–57.PubMedCrossRefGoogle Scholar
  17. Bhattacharya J, Goldman D, McCaffrey D. Estimating probit models with self-selected treatments. Stat Med. 2006;25:389–413.PubMedCrossRefGoogle Scholar
  18. Bhattacharya J, Shaikh A, Vytlacil E. Treatment effect bounds under monotonicity assumptions: an application to Swan-Ganz catheterization. Am Econ Rev. 2008;98:351–6.CrossRefGoogle Scholar
  19. Bound JD, Jaeger DA, Baker RM. Problems with instrumental variables estimation when the correlation between the instruments and the endogenous explanatory variables is weak. J Am Stat Assoc. 1995;90:443–50.Google Scholar
  20. Brookhart M, Schneeweiss S. Preference-based instrumental variable methods for the estimation of treatment effects: assessing validity and interpreting results. Int J Biostat. 2007;3:14.PubMedCentralCrossRefPubMedGoogle Scholar
  21. Brookhart M, Wang P, Solomon D, Schneeweiss S. Evaluating short-term drug effects using a physician-specific prescribing preference as an instrumental variable. Epidemiology. 2006;17:268–75.PubMedPubMedCentralCrossRefGoogle Scholar
  22. Brookhart M, Rassen J, Schneeweiss S. Instrumental variable methods in comparative safety and effectiveness research. Pharmacoepidemiol Drug Saf. 2010;19:537–54.PubMedPubMedCentralCrossRefGoogle Scholar
  23. Brooks J, Chrischilles E, Scott S, Chen-Hardee S. Was breast conserving surgery underutilized for early stage breast cancer? Instrumental variables evidence for stage II patients from Iowa. Health Serv Res. 2004;38:1385–402.CrossRefGoogle Scholar
  24. Bruce M, Ten Have T, Reynolds C III, Katz I, Schulberg H, Mulsant B, Brown G, McAvay G, Pearson J, Alexopoulos G. Reducing suicidal ideation and depressive symptoms in depressed older primary care patients: a randomized trial. J Am Med Assoc. 2004;291:1081–91.CrossRefGoogle Scholar
  25. Cai B, Small D, Ten Have T. Two-stage instrumental variable methods for estimating the causal odds ratio: analysis of bias. Stat Med. 2011;30:1809–24.PubMedCrossRefGoogle Scholar
  26. Cai B, Hennessy S, Flory JH, Sha D, Ten Have TR, Small DS. Simulation study of instrumental variable approaches with an application to a study of the antidiabetic effect of bezafibrate. Pharmacoepidemiol Drug Saf. 2012;21:114–20.PubMedCrossRefGoogle Scholar
  27. Card D. Using geographic variation in college proximity to estimate the return to schooling. Toronto: University of Toronto Press; 1995. p. 201–22.Google Scholar
  28. Cheng J. Estimation and inference for the causal effect of receiving treatment on a multinomial outcome. Biometrics. 2009;65:96–103.PubMedCrossRefGoogle Scholar
  29. Cheng J, Small D. Bounds on causal effects in three-arm trials with noncompliance. J R Stat Soc Ser B. 2006;68:815–36.CrossRefGoogle Scholar
  30. Cheng J, Qin J, Zhang B. Semiparametric estimation and inference for distributional and general treatment effects. J R Stat Soc Ser B Stat Methodol. 2009a;71:881–904.CrossRefGoogle Scholar
  31. Cheng J, Small D, Tan Z, Ten Have T. Efficient nonparametric estimation of causal effects in randomized trials with noncompliance. Biometrika. 2009b;96:19–36.CrossRefGoogle Scholar
  32. Clarke P, Windmeijer F. Instrumental variable estimators for binary outcomes. J Am Stat Assoc. 2012;107:1638–52.CrossRefGoogle Scholar
  33. Cole J, Norman H, Weatherby L, Walker A. Drug copayment and adherence in chronic heart failure: effect on costs and outcomes. Pharmacotherapy. 2006;26:1157–64.PubMedCrossRefPubMedCentralGoogle Scholar
  34. Cox D. Planning of experiments. New York: Wiley; 1958.Google Scholar
  35. Cuzick J, Sasieni P, Myles J, Tyler J. Estimating the effect of treatment in a proportional hazards model in the presence of non-compliance and contamination. J R Stat Soc Ser B Methodol. 2007;69:565–88.CrossRefGoogle Scholar
  36. Davidson R, MacKinnon J. Estimation and inference in econometrics. New York: Oxford University Press; 1993.Google Scholar
  37. Demissie K, Rhoads G, Ananth C, Alexander G, Kramer M, Kogan M, Joseph K. Trends in preterm birth and neonatal mortality among blacks and whites in the United States from 1989 to 1997. Am J Epidemiol. 2001;154:307–15.PubMedCrossRefPubMedCentralGoogle Scholar
  38. Didelez V, Sheehan N. Mendelian randomization as an instrumental variable approach to causal inference. Stat Methods Med Res. 2007;16:309–30.PubMedCrossRefPubMedCentralGoogle Scholar
  39. Durbin J. Errors in variables. Rev Inst Int Stat. 1954;22:23–32.CrossRefGoogle Scholar
  40. Fisher R. Design of experiments. Edinburgh: Oliver and Boyd; 1949.Google Scholar
  41. Freedman D. Statistical models: theory and practice. Cambridge: Cambridge University Press; 2009.CrossRefGoogle Scholar
  42. Freedman D, Sekhon J. Endogeneity in probit response models. Polit Anal. 2010;18:138–50.CrossRefGoogle Scholar
  43. Goedde H, Agarwal D, Fritze G, Meier-Tackmann D, Singh S, Beckmann G, Bhatia K, Chen L, Fang B, Lisker R. Distribution of ADH2 and ALDH2 genotypes in different populations. Hum Genet. 1992;88:344–6.PubMedCrossRefGoogle Scholar
  44. Goyal N, Zubizarreta J, Small D, Lorch S. Length of stay and readmission among late preterm infants: an instrumental variable approach. Hosp Pediatr. In press.Google Scholar
  45. Heckman J, Robb R. Alternative methods for evaluating the impacts of interventions: an overview. J Econ. 1985;30:239–67.CrossRefGoogle Scholar
  46. Heckman J, Vytlacil E. Local instrumental variables and latent variable models for identifying and bounding treatment effects. Proc Natl Acad Sci. 1999;96:4730–4.PubMedCrossRefGoogle Scholar
  47. Hernán M, Robins J. Instruments for causal inference: an epidemiologist’s dream? Epidemiology. 2006;17:360.PubMedCrossRefGoogle Scholar
  48. Hernán M, Robins J. Causal inference; 2013.Google Scholar
  49. Hirano K, Imbens G, Rubin D, Zhou X. Assessing the effect of an influenza vaccine in an encouragement design. Biostatistics. 2000;1:69–88.PubMedCrossRefGoogle Scholar
  50. Ho V, Hamilton B, Roos L. Multiple approaches to assessing the effects of delays for hip fracture patients in the United States and Canada. Health Serv Res. 2000;34:1499–518.PubMedPubMedCentralGoogle Scholar
  51. Ho D, Imai K, King G, Stuart E. Matching as nonparametric preprocessing for reducing model dependence in parametric causal inference. Polit Anal. 2007;15:199–236.CrossRefGoogle Scholar
  52. Hogan J, Lee J. Marginal structural quantile models for longitudinal observational studies with time-varying treatment. Stat Sin. 2004;14:927–44.Google Scholar
  53. Holland P. Causal inference, path analysis, and recursive structural equations models. Sociol Methodol. 1988;18:449–84.CrossRefGoogle Scholar
  54. Hudgens M, Halloran M. Towards causal inference with interference. J Am Stat Assoc. 2008;103:832–42.PubMedPubMedCentralCrossRefGoogle Scholar
  55. Hunink M, Glasziou P, Siegel J, Weeks J, Pliskin J, Elstein A, Weinstein M. Making in health and medicine: integrating evidence and values. Cambridge: Cambridge University Press; 2001.Google Scholar
  56. Imbens G. Nonadditive models with endogenous regressors. New York: Cambridge University Press; 2007.Google Scholar
  57. Imbens G, Angrist J. Identification and estimation of local average treatment effects. Econometrica. 1994;62:467–75.CrossRefGoogle Scholar
  58. Imbens G, Rosenbaum P. Robust, accurate confidence intervals with weak instruments: quarter of birth and education. J R Stat Soc Ser A. 2005;168:109–26.CrossRefGoogle Scholar
  59. Imbens G, Rubin D. Bayesian inference for causal effects in randomized experiments with noncompliance. Ann Stat. 1997a;25:305–27.CrossRefGoogle Scholar
  60. Imbens G, Rubin D. Estimating outcome distributions for compliers in instrumental variables models. Rev Econ Stud. 1997b;64:555–74.CrossRefGoogle Scholar
  61. Inoue A, Solon G. Two-sample instrumental variables estimators. Rev Econ Stat. 2010;92:557–61.CrossRefGoogle Scholar
  62. Joffe M. Administrative and artificial censoring in censored regression models. Stat Med. 2001;20:2287–304.PubMedCrossRefGoogle Scholar
  63. Joffe M. Principal stratification and attribution prohibition: good ideas taken too far. Int J Biostat. 2011;7(1):1–22.CrossRefGoogle Scholar
  64. Joffe M, Small D, Brunelli S, Ten Have T, Feldman H. Extended instrumental variables estimation for overall effects. Int J Biostat. 2008;4.Google Scholar
  65. Johnston S. Combining ecological and individual variables to reduce confounding by indication: case study – subarachnoid hemorrhage treatment. J Clin Epidemiol. 2000;53:1236–41.PubMedCrossRefGoogle Scholar
  66. Kang H, Kreuels B, Adjei O, May J, Small D. The causal effect of malaria on stunting: a Mendelian randomization and matching approach, Working Paper.Google Scholar
  67. Karni E. A theory of medical decision making under uncertainty. J Risk Uncertain. 2009;39:1–16.CrossRefGoogle Scholar
  68. Kaushal N. Do food stamps cause obesity? Evidence from immigrant experience. J Health Econ. 2007;26:968–91.PubMedCrossRefGoogle Scholar
  69. Kelejian H. Two-stage least squares and econometric systems linear in parameters but nonlinear in the endogenous variables. J Am Stat Assoc. 1971;66:373–4.CrossRefGoogle Scholar
  70. Kitcheman J, Adams C, Prevaiz A, Kader I, Mohandas D, Brookes G. Does an encouraging letter encourage attendance at psychiatric outpatient clinics? The Leeds PROMPTS randomized study. Psychol Med. 2008;38:717–23.PubMedCrossRefGoogle Scholar
  71. Korn E, Baumrind S. Clinician preferences and the estimation of causal treatment differences. Stat Sci. 1998;13:209–35.CrossRefGoogle Scholar
  72. Kramer M, Rooks Y, Pearson H. Growth and development in children with sickle-cell trait. N Engl J Med. 1978;299:686–9.PubMedCrossRefGoogle Scholar
  73. Lawlor D, Harbord R, Sterne J, Timpson N, Smith G. Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Stat Med. 2008;27:1133–63.PubMedCrossRefGoogle Scholar
  74. Little R, Yau L. Statistical techniques for analyzing data from prevention trials: treatment of no-shows using Rubin’s causal model. Psychol Methods. 1998;3:147–59.CrossRefGoogle Scholar
  75. Loeys T, Goetghebeur E. A causal proportional hazards estimator for the effect of treatment actually received in a randomized trial with all-or-nothing compliance. Biometrics. 2003;59:100–5.PubMedCrossRefGoogle Scholar
  76. Lorch S, Baiocchi M, Ahlberg C, Small D. The differential impact of delivery hospital on the outcomes of premature infants. Pediatrics. 2012a.Google Scholar
  77. Lorch S, Kroelinger C, Ahlberg C, Barfield W. Factors that mediate racial/ethnic disparities in us fetal death rates. Am J Public Health. 2012b;102:1902–10.PubMedPubMedCentralCrossRefGoogle Scholar
  78. Malkin J, Broder M, Keeler E. Do longer postpartum stays reduce newborn readmissions? Analysis using instrumental variables. Health Serv Res. 2000;35:1071–91.PubMedPubMedCentralGoogle Scholar
  79. McClellan M, McNeil B, Newhouse J. Does more intensive treatment of acute myocardial infarction in the elderly reduce mortality? Analysis using instrumental variables. JAMA. 1994;272:859.CrossRefGoogle Scholar
  80. Moreira M. A conditional likelihood ratio test for structural models. Econometrica. 1990;71:463–80.Google Scholar
  81. Muthen B. A structural probit model with latent variables. J Am Stat Assoc. 1979;74:807–11.Google Scholar
  82. Newman T, Vittinghoff E, McCulloch C. Efficacy of phototherapy for newborns with hyperbilirubinemia: a cautionary example of an instrumental variable analysis. Med Decis Mak. 2012;32:83–92.CrossRefGoogle Scholar
  83. Neyman J. On the application of probability theory to agricultural experiments. Stat Sci. 1990;5:463–80.CrossRefGoogle Scholar
  84. Nie H, Cheng J, Small D. Inference for the effect of treatment on survival probability in randomized trials with noncompliance and administrative censoring. Biometrics. 2011;67:1397–405.PubMedCrossRefGoogle Scholar
  85. O’Malley A, Frank R, Normand S. Estimating cost-offsets of new medications: use of new antipsychotics and mental health costs for schizophrenia. Stat Med. 2011;30:1971–88.PubMedPubMedCentralCrossRefGoogle Scholar
  86. Okui R, Small D, Tan Z, Robins J. Doubly robust instrumental variables regression. Stat Sin. 2012;22:173–205.CrossRefGoogle Scholar
  87. Owen A. Empirical likeliood. Boca Raton: Chapman & Hall/CRC; 2002.Google Scholar
  88. Pearl J. Causality. Cambridge: Cambridge University Press; 2009.CrossRefGoogle Scholar
  89. Permutt T, Hebel J. Simultaneous-equation estimation in a clinical trial of the effect of smoking on birth weight. Biometrics. 1989;45:619–22.PubMedCrossRefGoogle Scholar
  90. Phibbs C, Mark D, Luft H, Peltzman-Rennie D, Garnick D, Lichtenberg E, McPhee S. Choice of hospital for delivery: a comparison of high-risk and low-risk women. Health Serv Res. 1993;28:201.PubMedPubMedCentralGoogle Scholar
  91. Pliskin J, Shepard D, Weinstein M. Utility functions for life years and health status. Oper Res. 1980;28:206–24.CrossRefGoogle Scholar
  92. Poulson R, Gadbury G, Allison D. Treatment heterogeneity and individual qualitative interaction. Am Stat. 2012;66:16–24.PubMedPubMedCentralCrossRefGoogle Scholar
  93. Qin J, Zhang B. A goodness-of-fit test for logistic regression models based on case–control data. Biometrika. 1997;84:609–18.CrossRefGoogle Scholar
  94. Rehan N. Growth status of children with and without sickle cell trait. Clin Pediatr. 1981;20:705–9.CrossRefGoogle Scholar
  95. Robins J, Greenland S. A comment on Angrist, Imbens and Rubin: Identification of causal effects using instrumental variables. J Am Stat Assoc. 1996;91:456–8.Google Scholar
  96. Robins J, Tsiatis A. Correcting for non-compliance in randomized trials using rank preserving structural failure time models. Commun Stat Theory Methods. 1991;20:2609–31.CrossRefGoogle Scholar
  97. Rosenbaum P. Observational studies. New York: Springer; 2002.CrossRefGoogle Scholar
  98. Rosenbaum P. Design of observational studies. New York: Springer; 2009.Google Scholar
  99. Rosenbaum P, Rubin D. The central role of the propensity score in observational studies for causal effects. Biometrika. 1983;70:41–55.CrossRefGoogle Scholar
  100. Rubin D. Estimating causal effects of treatments in randomized and non-randomized studies. J Educ Psychol. 1974;66:688–701.CrossRefGoogle Scholar
  101. Rubin D. Formal modes of statistical inference for causal effects. J Stat Plan Inference. 1990;25:279–92.CrossRefGoogle Scholar
  102. Saigal S, Stoskopf B, Feeny D, Furlong W, Burrows E, Rosenbaum P, Hoult L. Differences in preferences for neonatal outcomes among health care professionals, parents, and adolescents. J Am Med Assoc. 1999;281:1991–7.CrossRefGoogle Scholar
  103. Sargan J. The estimation of economic relationships using instrumental variables. Econometrica. 1958;26:393–415.CrossRefGoogle Scholar
  104. Sexton M, Hebel J. A clinical trial of change in maternal smoking and its effect on birth weight. J Am Med Assoc. 1984;251:911–5.CrossRefGoogle Scholar
  105. Sham P. Statistics in human genetics. London: Arnold; 1998.Google Scholar
  106. Shea J. Instrument relevance in multivariate linear models: a simple measure. Rev Econ Stat. 1997;79:348–52.CrossRefGoogle Scholar
  107. Shetty K, Vogt W, Bhattacharya J. Hormone replacement therapy and cardiovascular health in the United States. Med Care. 2009;47:600–6.PubMedCrossRefGoogle Scholar
  108. Siddique Z. Partially identified treatment effects under imperfect compliance: the case of domestic violence. IZA Discussion Paper No. 4565. 2009.Google Scholar
  109. Small D. Sensitivity analysis for instrumental variables regression with overidentifying restrictions. J Am Stat Assoc. 2007;102:1049–58.CrossRefGoogle Scholar
  110. Small D, Rosenbaum P. War and wages: the strength of instrumental variables and their sensitivity to unobserved biases. J Am Stat Assoc. 2008;103:924–33.CrossRefGoogle Scholar
  111. Sobel M. What do randomized studies of housing mobility demonstrate? Causal inference in the face of interference. J Am Stat Assoc. 2006;101:1398–407.CrossRefGoogle Scholar
  112. Sommers BD, Beard CJ, Dahl D, D’Amico AV, Kaplan IP, Richie JP, Zeckhauser RJ. Decision analysis using individual patient preferences to determine optimal treatment for localized prostate cancer. Cancer. 2007;110:2210–7.PubMedCrossRefGoogle Scholar
  113. Stock J, Wright J, Yogo M. A survey of weak instruments and weak identification in generalized method of moments. J Bus Econ Stat. 2002;20:518–29.CrossRefGoogle Scholar
  114. Tan Z. Regression and weighting methods for causal inference using instrumental variables. J Am Stat Assoc. 2006;101:1607–18.CrossRefGoogle Scholar
  115. Tan Z. Marginal and nested structural models using instrumental variables. J Am Stat Assoc. 2010;105:157–69.CrossRefGoogle Scholar
  116. Ten Have T, Elliott M, Joffe M, Zanutto E, Datto C. Causal models for randomized physician encouragement trials in treating primary care depression. J Am Stat Assoc. 2004;99:16–25.CrossRefGoogle Scholar
  117. Terza J, Basu A, Rathouz P. Two-stage residual inclusion estimation: addressing endogeneity in health econometric modeling. Health Econ. 2008;27:527–43.Google Scholar
  118. Vansteelandt S, Bowden J, Babnezhad M, Goetghebeur E. On instrumental variables estimation of causal odds ratios. Stat Sci. 2011;26:403–22.CrossRefGoogle Scholar
  119. Voight B, Peloso G, Orho-Melander M, Frikke-Schmidt R, Barbalic M, Jensen M, Hindy G, Hólm H, Ding E, Johnson T, et al. Plasma HDL cholesterol and risk of myocardial infarction: a Mendelian randomisation study. Lancet. 2012;380:572–80.PubMedPubMedCentralCrossRefGoogle Scholar
  120. Vytlacil E. Independence, monotonicity, and latent index models: an equivalence result. Econometrica. 2002;70:331–41.CrossRefGoogle Scholar
  121. Wehby G, Jugessur A, Moreno L, Murray J, Wilcox A, Lie R. Genetic instrumental variable studies of the impacts of risk behaviors: an application to maternal smoking and orofacial clefts. Health Serv Outcome Res Methodol. 2011;11:54–78.CrossRefGoogle Scholar
  122. White H. Asymptotic theory for econometricians. 1984.Google Scholar
  123. Wooldridge J. On two stage least squares estimation of the average treatment effect in a random coefficient model. Econ Lett. 1997;56:129–33.CrossRefGoogle Scholar
  124. Zelen M. A new design for randomized clinical trials. N Engl J Med. 1979;300:1242–5.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of StatisticsStanford UniversityStanfordUSA
  2. 2.Department of Preventive and Restorative Dental SciencesUniversity of California, San Francisco School of DentistrySan FranciscoUSA
  3. 3.University of PennsylvaniaPhiladelphiaUSA

Personalised recommendations