Too Much Ado about Instrumental Variable Approach: Is the Cure Worse than the Disease?
dc.contributor.author | Baser, Onur | en_US |
dc.date.accessioned | 2010-06-01T20:13:59Z | |
dc.date.available | 2010-06-01T20:13:59Z | |
dc.date.issued | 2009-11 | en_US |
dc.identifier.citation | Baser, Onur (2009). "Too Much Ado about Instrumental Variable Approach: Is the Cure Worse than the Disease?." Value in Health 12(8): 1201-1209. <http://hdl.handle.net/2027.42/73354> | en_US |
dc.identifier.issn | 1098-3015 | en_US |
dc.identifier.issn | 1524-4733 | en_US |
dc.identifier.uri | https://hdl.handle.net/2027.42/73354 | |
dc.description.abstract | Objective: To review the efficacy of instrumental variable (IV) models in addressing a variety of assumption violations to ensure standard ordinary least squares (OLS) estimates are consistent. IV models gained popularity in outcomes research because of their ability to consistently estimate the average causal effects even in the presence of unmeasured confounding. However, in order for this consistent estimation to be achieved, several conditions must hold. In this article, we provide an overview of the IV approach, examine possible tests to check the prerequisite conditions, and illustrate how weak instruments may produce inconsistent and inefficient results. Methods: We use two IVs and apply Shea's partial R -square method, the Anderson canonical correlation, and Cragg–Donald tests to check for weak instruments. Hall–Peixe tests are applied to see if any of these instruments are redundant in the analysis. Results: A total of 14,952 asthma patients from the MarketScan Commercial Claims and Encounters Database were examined in this study. Patient health care was provided under a variety of fee-for-service, fully capitated, and partially capitated health plans, including preferred provider organizations, point of service plans, indemnity plans, and health maintenance organizations. We used controller–reliever copay ratio and physician practice/prescribing patterns as an instrument. We demonstrated that the former was a weak and redundant instrument producing inconsistent and inefficient estimates of the effect of treatment. The results were worse than the results from standard regression analysis. Conclusion: Despite the obvious benefit of IV models, the method should not be used blindly. Several strong conditions are required for these models to work, and each of them should be tested. Otherwise, bias and precision of the results will be statistically worse than the results achieved by simply using standard OLS. | en_US |
dc.format.extent | 104180 bytes | |
dc.format.extent | 3109 bytes | |
dc.format.mimetype | application/pdf | |
dc.format.mimetype | text/plain | |
dc.publisher | Blackwell Publishing Inc | en_US |
dc.rights | © 2009 International Society for Pharmacoeconomics and Outcomes Research | en_US |
dc.subject.other | Asthma | en_US |
dc.subject.other | Instrumental Variable | en_US |
dc.subject.other | Propensity Score | en_US |
dc.subject.other | Regression Analysis | en_US |
dc.title | Too Much Ado about Instrumental Variable Approach: Is the Cure Worse than the Disease? | en_US |
dc.type | Article | en_US |
dc.subject.hlbsecondlevel | Medicine (General) | en_US |
dc.subject.hlbtoplevel | Health Sciences | en_US |
dc.description.peerreviewed | Peer Reviewed | en_US |
dc.identifier.pmid | 19497084 | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/73354/1/j.1524-4733.2009.00567.x.pdf | |
dc.identifier.doi | 10.1111/j.1524-4733.2009.00567.x | en_US |
dc.identifier.source | Value in Health | en_US |
dc.identifier.citedreference | Baser O. Too much ado about propensity score models? Comparing methods of propensity score matching. Value Health 2006; 9: 377 – 85. | en_US |
dc.identifier.citedreference | Baser O. Choosing propensity score matching over regression adjustment for causal inference: when, why and how it makes sense. J Med Econ 2007; 10: 379 – 91. | en_US |
dc.identifier.citedreference | McClellan M. Uncertainty, health-care technologies, and health-care choices. Am Econ Rev 1995; 38 – 44. | en_US |
dc.identifier.citedreference | StÜrmer T, Joshi M, Glynn RJ, et al. A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods. J Clin Epidemiol 2006; 59: 437. e1–e24. | en_US |
dc.identifier.citedreference | Heckman JJ. Econometric causality. Int Stat Rev 2008; 76: 1 – 27. | en_US |
dc.identifier.citedreference | Ashenfelter O. Estimating the effect of training programs on earnings. Rev Econ Stat 1978; 60: 47 – 57. | en_US |
dc.identifier.citedreference | Ashenfelter O, Card D. Using the Longitudinal Structure of Earnings to Estimate the Effect of Training Programs. Working Papers 554, Princeton University, Department of Economics, Industrial Relations Section, 1984. | en_US |
dc.identifier.citedreference | Heckman J, Robb R. Alternative methods for evaluating the impact of interventions: an overview. J Econom 1985; 30: 239 – 67. | en_US |
dc.identifier.citedreference | LaLonde R. Evaluating the econometric evaluations of training programs with experimental data. Am Econ Rev 1986; 76: 604 – 20. | en_US |
dc.identifier.citedreference | Fraker T, Maynard R. The adequacy of comparison group designs for evaluations of employment-related programs. J Hum Resour 1987; 22: 194 – 227. | en_US |
dc.identifier.citedreference | Card D, Sullivan DG. Measuring the effect of subsidized training programs on movements in and out of employment. Econometrica 1988; 56: 497 – 530. | en_US |
dc.identifier.citedreference | Manski CF, Institute for Research on Poverty, University of Wisconsin–Madison. Identification of Endogenous Social Effects: The Reflection Problem. Madison, WI: University of Wisconsin–Madison, Institute for Research on Poverty, 1993. | en_US |
dc.identifier.citedreference | Imbens G, Wooldridge J. Recent Developments in the Econometrics of Program Evaluation. J Econ Lit 2009; 47: 5 – 86. | en_US |
dc.identifier.citedreference | Newhouse JP, McClellan M. Econometrics in outcomes research: the use of instrumental variables. Annu Rev Public Health 1998; 19: 17 – 34. | en_US |
dc.identifier.citedreference | Clever SL, Jin L, Levinson W, Meltzer DO. Does doctor-patient communication affect patient satisfaction with hospital care? Results of an analysis with a novel instrumental variable. Health Serv Res 2008; 43: 1505 – 19. | en_US |
dc.identifier.citedreference | Johnston MK, Gustafson P, Levy AR, Grootendorst P. Use of instrumental variables in the analysis of generalized linear models in the presence of unmeasured confounding with applications to empidemiological research. Stat Med 2008; 27: 1539 – 56. | en_US |
dc.identifier.citedreference | Grootendorst P. A review of instrumental variables estimation of treatment effects in the applied health sciences. Health Serv Outcomes Res Methodol 2007; 7: 159 – 79. | en_US |
dc.identifier.citedreference | Basu A, Heckman JJ, 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. J Health Econ (Chichester) 2007; 16: 1133. | en_US |
dc.identifier.citedreference | Eisenberg D, Quinn BC. Estimating the effect of smoking cessation on weight gain: an instrumental variable approach. Health Serv Res 2006; 41: 2255 – 66. | en_US |
dc.identifier.citedreference | Wooldridge JM. Introductory Econometrics: A Modern Approach ( 3rd ed. ). Mason, OH: Thomson/South-Western, 2006. | en_US |
dc.identifier.citedreference | Wooldridge JM. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA: MIT Press, 2002. | en_US |
dc.identifier.citedreference | Bowden RJ, Turkington DA. Instrumental Variables. Cambridge: Cambridge University Press, 1984. | en_US |
dc.identifier.citedreference | Kelejian HH, Prucha IR. A generalized spatial two-stage least squares procedure for estimating a spatial autoregressive model with autoregressive disturbances. J Real Estate Finance Econ 1998; 17: 99 – 121. | en_US |
dc.identifier.citedreference | Amemiya T. The nonlinear two-stage least-squares estimator. J Econom 1974; 2: 105 – 10. | en_US |
dc.identifier.citedreference | Rivers D, Vuong QH. Limited information estimators and exogeneity tests for simultaneous probit models. J Econom 1988; 39: 347 – 66. | en_US |
dc.identifier.citedreference | MÁtyÁs L. Generalized Method of Moments Estimation. Cambridge: Cambridge University Press, 1999. | en_US |
dc.identifier.citedreference | Dow WH, Norton EC. Choosing between and interpreting the heckit and two-part models for corner solutions. Health Serv Outcomes Res Methodol 2003; 4: 5 – 18. | en_US |
dc.identifier.citedreference | Fisher ES, Wennberg DE, Stukel TA, et al. The implications of regional variations in medicare spending. Part 1: the content, quality, and accessibility of care. Ann Intern Med 2003; 138: 273 – 87. | en_US |
dc.identifier.citedreference | Altonji JG, Elder TE, Taber C. An evaluation of instrumental variable strategies for estimating the effects of catholic schools. J Human Res 2005; 4: 791 – 821. | en_US |
dc.identifier.citedreference | Rodrik D. Getting institutions right. CESifo DICE Rep 2004; 2: 10 – 15. | en_US |
dc.identifier.citedreference | Miguel E, Satyanath S, Sergenti E. Economic shocks and civil conflict: an instrumental variables approach. J Polit Econ 2004; 112: 725 – 53. | en_US |
dc.identifier.citedreference | Fisher ES, Wennberg DE, Stukel TA, et al. The implications of regional variations in medicare spending. Part 2: health outcomes and satisfaction with care. Ann Intern Med 2003; 138: 288 – 98. | en_US |
dc.identifier.citedreference | Witzke H. Determinants of the US wheat producer support price: do presidential elections matter? Public Choice 1990; 64: 155 – 65. | en_US |
dc.identifier.citedreference | Revelli F. Local taxes, national politics and spatial interactions in English district election results. Eur J Polit Econ 2002; 18: 281 – 99. | en_US |
dc.identifier.citedreference | Breitung J, Meyer W. Testing for unit roots in panel data: are wages on different bargaining levels cointegrated? Appl Econ 1994; 26: 353 – 61. | en_US |
dc.identifier.citedreference | Angrist JD, Krueger AB. Instrumental variables and the search for identification: from supply and demand to natural experiments. J Econ Perspect 15: 69 – 85. | en_US |
dc.identifier.citedreference | Hansen LP, Singleton KJ. Generalized instrumental variables estimation of nonlinear rational expectations models. Econometrica 1982; 50: 1269 – 86. | en_US |
dc.identifier.citedreference | Howard D. The impact of waiting time on liver transplant outcomes. Health Serv Res. 2000; 35 ( 5 Pt 2 ): 1117. | en_US |
dc.identifier.citedreference | Sacerdote B. Peer effects with random assignment: results for Dartmouth roommates. Q J Econ 2001; 116: 681 – 704. | en_US |
dc.identifier.citedreference | Miller WB, Pasta DJ. The psychology of child timing: a measurement instrument and a Model 1. J Appl Soc Psychol 1994; 24: 218 – 50. | en_US |
dc.identifier.citedreference | Hedges LV. Modeling publication selection effects in meta-analysis. Stat Sci 1992; 7: 246 – 55. | en_US |
dc.identifier.citedreference | Kinal TW. The existence of moments of k-class estimators. Econometrica 1980; 48: 241 – 50. | en_US |
dc.identifier.citedreference | Staiger D, Stock JH. Instrumental variables regression with weak instruments. Econometrica (Evanston, Ill) 1997; 65: 557 – 86. | en_US |
dc.identifier.citedreference | Chao JC, Swanson NR. Consistent estimation with a large number of weak instruments. Econometrica 2005; 73: 1673 – 92. | en_US |
dc.identifier.citedreference | Bound J, Jaeger DA, Baker RM. Problems with instrumental variables estimation when the correlation between the instruments and the endogenous explanatory variable is weak. J Am Stat Assoc 1995; 90: 443 – 50. | en_US |
dc.identifier.citedreference | Shea J. Instrument relevance in multivariate linear models: a simple measure. Rev Econ Stat 1997; 79: 348 – 52. | en_US |
dc.identifier.citedreference | Anderson TW. An Introduction to Multivariate Analysis. New York: Wiley, 1958. | en_US |
dc.identifier.citedreference | Hall AR, Peixe FPM. A consistent method for the selection of relevant instruments. Econom Rev 2003; 22: 269 – 87. | en_US |
dc.identifier.citedreference | Cragg JG, Donald SG. Inferring the rank of a matrix. J Econom 1997; 76: 223 – 50. | en_US |
dc.identifier.citedreference | Stock JH, Yogo M. Testing for Weak Instruments in Linear IV Regression. NBER Working Paper T0284, 2002. | en_US |
dc.identifier.citedreference | Crown WH, Berndt ER, Baser O, et al. Benefit plan design and prescription drug utilization among asthmatics: do patient copayments matter? Front Health Policy Res 2004; 7: 95 – 127. | en_US |
dc.identifier.citedreference | Hausman J. Specification tests in econometrics. Econometrica 1978; 46: 1251 – 71. | en_US |
dc.identifier.citedreference | Hausman J, Taylor W. Panel data and unobservable individual effects. Econometrica 1981; 49: 1377 – 98. | en_US |
dc.identifier.citedreference | Manning WG, Mullahy J. Estimating log models: to transform or not to transform? J Health Econ 2001; 20: 461 – 94. | en_US |
dc.identifier.citedreference | Shea D, Terza J, Stuart B, Briesacher B. Estimating the effects of prescription drug coverage for medicare beneficiaries. Health Serv Res 2007; 42 ( 3 Pt 1 ): 933. | en_US |
dc.identifier.citedreference | Stukel TA, Fisher ES, Wennberg DE, et al. Analysis of observational studies in the presence of treatment selection bias: effects of invasive cardiac management on AMI survival using propensity score and instrumental variable methods. JAMA 2007; 297: 278 – 85. | en_US |
dc.owningcollname | Interdisciplinary and Peer-Reviewed |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.