An Instrumental Variable Forest Approach for Detecting Heterogeneous Treatment Effects in Observational Studies

References

• Athey S, Imbens G (2016) Recursive partitioning for heterogeneous causal effects. Proc. Natl. Acad. Sci. USA 113(27):7353–7360.Crossref, Google Scholar
• Athey S, Tibshirani J, Wager S (2019) Generalized random forests. Ann. Statist. 47(2):1148–1178.Crossref, Google Scholar
• Ayanian JZ, Weissman JS (2002) Teaching hospitals and quality of care: A review of the literature. Milbank Quart. 80(3):569–593.Crossref, Google Scholar
• Bargagli Stoffi FJB, Gnecco G (2020) Causal tree with instrumental variable: An extension of the causal tree framework to irregular assignment mechanisms. Internat. J. Data Sci. Anal. 9:315–337.Crossref, Google Scholar
• Bartel AP, Chan CW, Kim SH (2020) Should hospitals keep their patients longer? The role of inpatient care in reducing postdischarge mortality. Management Sci. 66(6):2326–2346.Google Scholar
• Bastani H, Goh J, Bayati M (2019) Evidence of upcoding in pay-for-performance programs. Management Sci. 65(3):1042–1060.Link, Google Scholar
• Bavafa H, Hitt LM, Terwiesch C (2018) The impact of e-visits on visit frequencies and patient health: Evidence from primary care. Management Sci. 64(12):5461–5480.Link, Google Scholar
• Boscoe FP, Henry KA, Zdeb MS (2012) A nationwide comparison of driving distance vs. straight-line distance to hospitals. Professional Geographer 64(2):188–196.Crossref, Google Scholar
• Breen R, Choi S, Holm A (2015) Heterogeneous causal effects and sample selection bias. Sociol. Sci. 2:351–369.Crossref, Google Scholar
• Breiman L (2001) Random forests. Machine Learn. 45(1):5–32.Crossref, Google Scholar
• Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and Regression Trees (CRC Press, Boca Raton, FL).Google Scholar
• Brooks JM, Irwin CP, Hunsicker LG, Flanigan MJ, Chrischilles EA, Pendergast JF (2006) Effect of dialysis center profit-status on patient survival: A comparison of risk-adjustment and instrumental variable approaches. Health Services Res. 41(6):2267–2289.Crossref, Google Scholar
• Chipman HA, George EI, McCulloch RE (2010) BART: Bayesian additive regression trees. Ann. Appl. Statist. 4(1):266–298.Crossref, Google Scholar
• Chan CW, Farias VF, Escobar GJ (2016) The impact of delays on service times in the intensive care unit. Management Sci. 63(7):2049–2072.Link, Google Scholar
• Duggirala AV, Chen FM, Gergen PJ (2004) Postoperative adverse events in teaching and nonteaching hospitals. Family Medicine 36(7):508–513.Google Scholar
• Ferreira KJ, Lee BHA, Simchi-Levi D (2015) Analytics for an online retailer: Demand forecasting and price optimization. Manufacturing Service Oper. Management 18(1):69–88.Link, Google Scholar
• Fineberg SJ, Oglesby M, Patel AA, Pelton MA, Singh K (2013) Outcomes of cervical spine surgery in teaching and non-teaching hospitals. Spine 38(13):1089–1096.Crossref, Google Scholar
• Freeman M, Savva N, Scholtes S (2016) Gatekeepers at work: An empirical analysis of a maternity unit. Management Sci. 63(10):3147–3167.Link, Google Scholar
• Friedberg R, Tibshirani J, Athey S, Wager S (2020) Local linear forests. J. Comput. Graph Statist. 30(2):1–15.Google Scholar
• Friedman J, Hastie T, Tibshirani R (2001) The Elements of Statistical Learning, Springer Series in Statistics, vol. 1, no. 10 (Springer, New York).Google Scholar
• Gopaldas RR, Bakaeen FG, Dao TK, Coselli JS, LeMaire SA, Huh J, Chu D (2012) Outcomes of concomitant aortic valve replacement and coronary artery bypass grafting at teaching hospitals vs. nonteaching hospitals. J. Thoracic Cardiovascular Surgery 143(3):648–655.Crossref, Google Scholar
• Gowrisankaran G, Town RJ (1999) Estimating the quality of care in hospitals using instrumental variables. J. Health Econom. 18(6):747–767.Crossref, Google Scholar
• Greene WH (2003) Econometric Analysis, 5th ed. (Prentice Hall, Upper Saddle River, NJ).Google Scholar
• Hahn PR, Murray J, Carvalho CM (2020) Bayesian regression tree models for causal inference: Regularization, confounding, and heterogeneous effects (with discussion). Bayesian Anal. 15(3):965–1056.Google Scholar
• Heller R, Rosenbaum PR, Small DS (2009) Split samples and design sensitivity in observational studies. J. Amer. Statist. Assoc. 104(487):1090–1101.Crossref, Google Scholar
• Ho V, Hamilton BH, Roos LL (2000) Multiple approaches to assessing the effects of delays for hip fracture patients in the United States and Canada. Health Services Res. 34(7):1499–1518.Google Scholar
• Hothorn T, Hornik K, Zeileis A (2006) Unbiased recursive partitioning: A conditional inference framework. J. Comput. Graphical Statist. 15(3):651–674.Crossref, Google Scholar
• Ibanez MR, Clark JR, Huckman RS, Staats BR (2017) Discretionary task ordering: Queue management in radiological services. Management Sci. 64(9):4389–4407.Link, Google Scholar
• Imai K, Ratkovic M (2013) Estimating treatment effect heterogeneity in randomized program evaluation. Ann. Appl. Statist. 7(1):443–470.Crossref, Google Scholar
• KC DS, Terwiesch C (2011) The effects of focus on performance: Evidence from California hospitals. Management Sci. 57(11):1897–1912.Link, Google Scholar
• KC DS, Terwiesch C (2012) An econometric analysis of patient flows in the cardiac intensive care unit. Manufacturing Service Oper. Management 14(1):50–65.Link, Google Scholar
• Kent DM, Hayward RA (2007) Limitations of applying summary results of clinical trials to individual patients: The need for risk stratification. JAMA 298(10):1209–1212.Crossref, Google Scholar
• Khuri SF, Najjar SF, Daley J, Krasnicka B, Hossain M, Henderson WG, Aust JB, et al. (2001) Comparison of surgical outcomes between teaching and nonteaching hospitals in the Department of Veterans Affairs. Ann. Surgery 234(3):370–382.Crossref, Google Scholar
• Kim SH, Chan CW, Olivares M, Escobar G (2014) ICU admission control: An empirical study of capacity allocation and its implication for patient outcomes. Management Sci. 61(1):19–38.Link, Google Scholar
• King G, Nielsen R (2019) Why propensity scores should not be used for matching. Political Anal. 27(4):435–454.Google Scholar
• Kravitz RL, Duan N, Braslow J (2004) Evidence-based medicine, heterogeneity of treatment effects, and the trouble with averages. Milbank Quart. 82(4):661–687.Crossref, Google Scholar
• Lacy AM, García-Valdecasas JC, Delgado S, Castells A, Taurá P, Piqué JM, Visa J (2002) Laparoscopy-assisted colectomy vs. open colectomy for treatment of non-metastatic colon cancer: A randomised trial. Lancet 359(9325):2224–2229.Crossref, Google Scholar
• Lee DD, Li J, Wang G, Croome KP, Burns JM, Perry DK, Nguyen JH, Hopp WJ, Taner CB (2017) Looking inward: The impact of operative time on graft survival after liver transplantation. Surgery 162(4):937–949.Crossref, Google Scholar
• Levi R, Paulson E, Perakis G (2020) Fresh fruit and vegetable consumption: The impact of access and value. Working paper, Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA.Google Scholar
• Lieberman JA, Stroup TS, McEvoy JP, Swartz MS, Rosenheck RA, Perkins DO, Keefe RSE (2005) Effectiveness of antipsychotic drugs in patients with chronic schizophrenia. New England J. Medicine 2005(353):1209–1223.Crossref, Google Scholar
• Listl S, Jürges H, Watt RG (2016) Causal inference from observational data. Community Dentistry Oral Epidemiology 44(5):409–415.Crossref, Google Scholar
• Lu SF, Rui H, Seidmann A (2018) Does technology substitute for nurses? Staffing decisions in nursing homes. Management Sci. 64(4):1842–1859.Link, Google Scholar
• Mant D (1999) Can randomised trials inform clinical decisions about individual patients? Lancet 353(9154):743–746.Crossref, Google Scholar
• Masoomi H, Wirth GA, Paydar KZ, Richland BK, Evans GR (2014) Perioperative outcomes of autologous breast reconstruction surgery in teaching vs. nonteaching hospitals. Plastic Reconstructive Surgery 134(4):514e–520e.Crossref, Google Scholar
• McClellan M, McNeil BJ, Newhouse JP (1994) Does more intensive treatment of acute myocardial infarction in the elderly reduce mortality? Analysis using instrumental variables. JAMA 272(11):859–866.Crossref, Google Scholar
• McConnell KJ, Newgard CD, Mullins RJ, Arthur M, Hedges JR (2005) Mortality benefit of transfer to level I vs. level II trauma centers for head-injured patients. Health Services Res. 40(2):435–458.Crossref, Google Scholar
• Meinshausen N (2006) Quantile regression forests. J. Machine Learn. Res. 7(June):983–999.Google Scholar
• Moss RR, Humphries KH, Gao M, Thompson CR, Abel JG, Fradet G, Munt BI (2003) Outcome of mitral valve repair or replacement: A comparison by propensity score analysis. Circulation 108(Suppl 1):II90–II97.Crossref, Google Scholar
• Nandyala SV, Marquez-Lara A, Fineberg SJ, Hassanzadeh H, Singh K (2014) Complications after lumbar spine surgery between teaching and nonteaching hospitals. Spine 39(5):417–423.Crossref, Google Scholar
• Nie X, Wager S (2021) Quasi-oracle estimation of heterogeneous treatment effects. Biometrika 108(2):299–319.Google Scholar
• Porembka MR, Hall BL, Hirbe M, Strasberg SM (2010) Quantitative weighting of postoperative complications based on the accordion severity grading system: Demonstration of potential impact using the American College of Surgeons national surgical quality improvement program. J. Amer. College Surgeons 210(3):286–298.Crossref, Google Scholar
• Powers S, Qian J, Jung K, Schuler A, Shah NH, Hastie T, Tibshirani R (2018) Some methods for heterogeneous treatment effect estimation in high-dimensions. Statist. Medicine 37(11):1767–1787.Google Scholar
• Sexton J, Laake P (2009) Standard errors for bagged and random forest estimators. Comput. Statist. Data Anal. 53(3):801–811.Crossref, Google Scholar
• Strasberg SM, Hall BL (2011) Postoperative morbidity index: A quantitative measure of severity of postoperative complications. J. Amer. College Surgeons 213(5):616–626.Crossref, Google Scholar
• Su X, Tsai CL, Wang H, Nickerson DM, Li B (2009) Subgroup analysis via recursive partitioning. J. Machine Learn. Res. 10(Feb):141–158.Google Scholar
• Taddy M, Gardner M, Chen L, Draper D (2016) A nonparametric Bayesian analysis of heterogenous treatment effects in digital experimentation. J. Bus. Econom. Statist. 34(4):661–672.Crossref, Google Scholar
• Tan TF, Netessine S (2014) When does the devil make work? An empirical study of the impact of workload on worker productivity. Management Sci. 60(6):1574–1593.Link, Google Scholar
• Taylor DH Jr, Whellan DJ, Sloan FA (1999) Effects of admission to a teaching hospital on the cost and quality of care for Medicare beneficiaries. New England J. Medicine 340(4):293–299.Crossref, Google Scholar
• Thornlow DK, Stukenborg GJ (2006) The association between hospital characteristics and rates of preventable complications and adverse events. Medical Care 44(3):265–269.Crossref, Google Scholar
• Tian L, Alizadeh AA, Gentles AJ, Tibshirani R (2014) A simple method for estimating interactions between a treatment and a large number of covariates. J. Amer. Statist. Assoc. 109(508):1517–1532.Crossref, Google Scholar
• Vapnik VN, Chervonenkis AY (1971) On the uniform convergence of relative frequencies of events to their probabilities. Probab. Appl. 17(2):264–280.Crossref, Google Scholar
• Vartak S, Ward MM, Vaughn TE (2008) Do postoperative complications vary by hospital teaching status? Medical Care 46(1):25–32.Crossref, Google Scholar
• Vuik SI, Mayer EK, Darzi A (2016) Patient segmentation analysis offers significant benefits for integrated care and support. Health Affairs 35(5):769–775.Crossref, Google Scholar
• Wager S, Athey S (2018) Estimation and inference of heterogeneous treatment effects using random forests. J. Amer. Statist. Assoc. 113(523):1228–1242.Crossref, Google Scholar
• Wager S, Hastie T, Efron B (2014) Confidence intervals for random forests: The jackknife and the infinitesimal jackknife. J. Machine Learn. Res. 15(1):1625–1651.Google Scholar
• Xie Y, Brand JE, Jann B (2012) Estimating heterogeneous treatment effects with observational data. Sociol. Methodology 42(1):314–347.Crossref, Google Scholar
• Xu Y, Armony M, Ghose A (2021) The interplay between online reviews and physician demand: An empirical investigation. Management Sci Forthcoming.Google Scholar
• Zeileis A, Hothorn T, Hornik K (2008) Model-based recursive partitioning. J. Comput. Graphical Statist. 17(2):492–514.Crossref, Google Scholar