×

zbMATH — the first resource for mathematics

Partial identification of the average treatment effect using instrumental variables: review of methods for binary instruments, treatments, and outcomes. (English) Zbl 1398.92009
J. Am. Stat. Assoc. 113, No. 522, 933-947 (2018); correction ibid. 115, No. 530, 1035-1036 (2020).
Summary: Several methods have been proposed for partially or point identifying the average treatment effect (ATE) using instrumental variable (IV) type assumptions. The descriptions of these methods are widespread across the statistical, economic, epidemiologic, and computer science literature, and the connections between the methods have not been readily apparent. In the setting of a binary instrument, treatment, and outcome, we review proposed methods for partial and point identification of the ATE under IV assumptions, express the identification results in a common notation and terminology, and propose a taxonomy that is based on sets of identifying assumptions. We further demonstrate and provide software for the application of these methods to estimate bounds.

MSC:
92B10 Taxonomy, cladistics, statistics in mathematical biology
62P10 Applications of statistics to biology and medical sciences; meta analysis
92-04 Software, source code, etc. for problems pertaining to biology
Software:
bpbounds; Stata; TETRAD
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Angrist, J. D.; Imbens, G. W.; Rubin, D. B., Identification of causal effects using instrumental variables, Journal of the American Statistical Association, 91, 444-455, (1996) · Zbl 0897.62130
[2] Baiocchi, M.; Cheng, J.; Small, D. S., Instrumental variable methods for causal inference, Statistics in Medicine, 33, 2297-2340, (2014)
[3] Baker, S. G.; Lindeman, K. S., The paired availability design: A proposal for evaluating epidural analgesia during labor, Statistics in Medicine, 13, 2269-2278, (1994)
[4] Balke, A.; Pearl, J., Bounds on treatment effects from studies with imperfect compliance, Journal of the American Statistical Association, 92, 1171-1176, (1997) · Zbl 0888.62049
[5] Beresteanu, A.; Manski, C. F., Bounds for stata, (2000)
[6] Beresteanu, A.; Molchanov, I.; Molinari, F., Partial identification using random set theory, Journal of Econometrics, 166, 17-32, (2012) · Zbl 1441.62607
[7] Bhattacharya, J.; Shaikh, A. M.; Vytlacil, E., Treatment effect bounds under monotonicity assumptions: an application to swan-ganz catheterization, The American Economic Review, 98, 351-356, (2008)
[8] Blanco, G.; Flores, C. A.; Flores-Lagunes, A., Bounds on average and quantile treatment effects of job corps training on wages, Journal of Human Resources, 48, 659-701, (2013)
[9] Bonet, B., Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence, Instrumentality tests revisited, 48-55, (2001), Morgan Kaufmann Publishers Inc.
[10] Cai, Z.; Kuroki, M.; Pearl, J.; Tian, J., Bounds on direct effects in the presence of confounded intermediate variables, Biometrics, 64, 695-701, (2008) · Zbl 1274.62737
[11] Chernozhukov, V.; Hansen, C., An IV model of quantile treatment effects, Econometrica, 73, 245-261, (2005) · Zbl 1152.91706
[12] Chernozhukov, V.; Kim, W.; Lee, S.; Rosen, A. M., Implementing intersection bounds in stata, Stata Journal, 15, 21-44, (2015)
[13] Chesher, A., Instrumental variable models for discrete outcomes, Econometrica, 78, 575-601, (2010) · Zbl 1229.60015
[14] Davies, N. M.; Smith, G. D.; Windmeijer, F.; Martin, R. M., Issues in the reporting and conduct of instrumental variable studies: A systematic review, Epidemiology, 24, 363-369, (2013)
[15] Dawid, A.; Green, P. J.; Hjort, N. L.; Richardson, S., Highly Structured Stochastic Systems, Causal inference using influence diagrams: the problem of partial compliance, 45-81, (2003), Oxford University Press, Oxford
[16] Didelez, V.; Meng, S.; Sheehan, N. A., Assumptions of IV methods for observational epidemiology, Statistical Science, 25, 22-40, (2010) · Zbl 1328.62587
[17] Didelez, V.; Sheehan, N., Mendelian randomization as an instrumental variable approach to causal inference, Statistical Methods in Medical Research, 16, 309-330, (2007) · Zbl 1122.62343
[18] Finkelstein, A., Oregon health insurance experiment public use data, (2013)
[19] Flores, C. A.; Flores-Lagunes, A., Partial identification of local average treatment effects with an invalid instrument, Journal of Business & Economic Statistics, 31, 534-545, (2013)
[20] Greenland, S.; Pearl, J.; Robins, J. M., Causal diagrams for epidemiologic research, Epidemiology, 10, 37-48, (1999)
[21] Heckman, J. J.; Vytlacil, E. J., Instrumental Variables, Selection Models, and Tight Bounds on the Average Treatment Effect, (2001), Springer, New York
[22] Hernán, M. A.; Robins, J. M., Instruments for causal inference: an epidemiologist’s dream?, Epidemiology, 17, 360-372, (2006)
[23] Huber, M., Sensitivity checks for the local average treatment effect, Economics Letters, 123, 220-223, (2014)
[24] Huber, M.; Laffers, L.; Mellace, G., Sharp IV bounds on average treatment effects on the treated and other populations under endogeneity and noncompliance, Journal of Applied Econometrics, 32, 56-79, (2015)
[25] Huber, M.; Mellace, G., Testing instrument validity for late identification based on inequality moment constraints, Review of Economics and Statistics, 97, 398-411, (2015)
[26] Hudgens, M. G.; Hoering, A.; Self, S. G., On the analysis of viral load endpoints in HIV vaccine trials, Statistics in Medicine, 22, 2281-2298, (2003)
[27] Imai, K., Sharp bounds on the causal effects in randomized experiments with ‘truncation-by-death’, Statistics & Probability Letters, 78, 144-149, (2008) · Zbl 1131.62099
[28] Imbens, G. W.; Angrist, J. D., Identification and estimation of local average treatment effects, Econometrica, 62, 467-475, (1994) · Zbl 0800.90648
[29] Kaufman, S.; Kaufman, J. S.; MacLehose, R. F., Analytic bounds on causal risk differences in directed acyclic graphs involving three observed binary variables, Journal of Statistical Planning and Inference, 139, 3473-3487, (2009) · Zbl 1186.62131
[30] Kitagawa, T., Identification region of the potential outcome distributions under instrument independence, (2009), CEMMAP, London, UK
[31] A test for instrument validity, Econometrica, 83, 2043-2063, (2015) · Zbl 1410.62042
[32] Kreider, B.; Hill, S. C., Partially identifying treatment effects with an application to covering the uninsured, Journal of Human Resources, 44, 409-449, (2009)
[33] Manski, C. F., Nonparametric bounds on treatment effects, The American Economic Review, 80, 319-323, (1990)
[34] Monotone treatment response, Econometrica: Journal of the Econometric Society, 65, 1311-1334, (1997) · Zbl 0906.62126
[35] Partial Identification of Probability Distributions, (2003), Springer Science & Business Media, New York
[36] Manski, C. F.; Pepper, J. V., Monotone instrumental variables: with an application to the returns to schooling, Econometrica, 68, 997-1010, (2000) · Zbl 1016.62133
[37] How do right-to-carry laws affect crime rates? coping with ambiguity using bounded-variation assumptions, Review of Economics and Statistics, 100, 232-244, (2015)
[38] McCarthy, I.; Millimet, D. L.; Roy, M., Bounding treatment effects: stata command for the partial identification of the average treatment effect with endogenous and misreported treatment assignment, Stata Journal, 15, 411-436, (2015)
[39] Mealli, F.; Pacini, B., Using secondary outcomes to sharpen inference in randomized experiments with noncompliance, Journal of the American Statistical Association, 108, 1120-1131, (2013) · Zbl 06224991
[40] Mourifie, I.; Wan, Y., Testing local average treatment effect assumptions, Review of Economics and Statistics, 99, 305-313, (2014)
[41] Palmer, T. M.; Ramsahai, R. R.; Didelez, V.; Sheehan, N. A., Nonparametric bounds for the causal effect in a binary instrumental-variable model, Stata Journal, 11, 345-367, (2011)
[42] Pearl, J., On the testability of causal models with latent and instrumental variables, Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence (UAI), 435-443, (1995), Morgan Kaufmann, Burlington
[43] Causality: Models, Reasoning and Inference, (2000), Cambridge University Press. [Errata Available at: ], Cambridge · Zbl 0959.68116
[44] Ramsahai, R. R., Causal bounds and observable constraints for non-deterministic models, The Journal of Machine Learning Research, 13, 829-848, (2012) · Zbl 1283.68299
[45] Richardson, T. S.; Evans, R. J.; Robins, J. M.; J. M., Bernardo; M. J., Bayarri; J. O., Berger; A. P., Dawid; D., Heckerman; A. F. M., Smith; M., West, Bayesian Statistics 9, Transparent parametrizations of models for potential outcomes, 569-610, (2010), Oxford University Press, Oxford
[46] Richardson, T. S.; Robins, J. M.; R., Dechter; H., Geffner; J. Y., Halpern, Analysis of the binary instrumental variable model, Heuristics, Probability and Causality: A Tribute to Judea Pearl, 415-444, (2010), London College Publications, London · Zbl 1223.68109
[47] Single world intervention graphs (SWIGs): A unification of the counterfactual and graphical approaches to causality, (2013)
[48] ACE bounds; SEMs with equilibrium conditions, Statistical Science, 29, 363-366, (2014) · Zbl 1331.62481
[49] Robins, J., A new approach to causal inference in mortality studies with sustained exposure periods – applications to control of the healthy worker survivor effect, Mathematical Modeling, 7, 1393-1512, (1986) · Zbl 0614.62136
[50] The Analysis of Randomized and Non-Randomized AIDS Treatment Trials Using a New Approach to Causal Inference in Longitudinal StudiesWashington, DCNCHRS, US Public Health Service
[51] Correcting for non-compliance in randomized trials using structural nested mean models, Communications in Statistics-Theory and Methods, 23, 2379-2412, (1994) · Zbl 0825.62203
[52] Robins, J. M.; Greenland, S., Identification of causal effects using instrumental variables: comment, Journal of the American Statistical Association, 91, 456-458, (1996)
[53] Robins, J. M.; Richardson, T. S.; Shrout, P.; Keyes, K.; Ornstein, K., Causality and Psychopathology: Finding the Determinants of Disorders and Their Cures, Alternative graphical causal models and the identification of direct effects, (2011), Oxford University Press, pp. 1-52, Oxford
[54] Siddique, Z., Partially identified treatment effects under imperfect compliance: the case of domestic violence, Journal of the American Statistical Association, 108, 504-513, (2013) · Zbl 06195956
[55] Spirtes, P.; Glymour, C.; Scheines, R., Causation, Prediction and Search, (1993), Springer-Verlag, Vol. 81), New York · Zbl 0806.62001
[56] Sprecher, D. L.; Schaefer, E. J.; Kent, K. M.; Gregg, R. E.; Zech, L. A.; Hoeg, J. M.; McManus, B.; Roberts, W. C.; Brewer, H. B., Cardiovascular features of homozygous familial hypercholesterolemia: analysis of 16 patients, The American Journal of Cardiology, 54, 20-30, (1984)
[57] Swanson, S. A.; Holme, Ø.; Løberg, M.; Kalager, M.; Bretthauer, M.; Hoff, G.; Aas, E.; Hernán, M. A., Bounding the per-protocol effect in randomized trials: an application to colorectal cancer screening, Trials, 16, 1-11, (2015)
[58] Taubman, S. L.; Allen, H. L.; Wright, B. J.; Baicker, K.; Finkelstein, A. N., Medicaid increases emergency-department use: evidence from oregon’s health insurance experiment, Science, 343, 263-268, (2014)
[59] VanderWeele, T. J.; Tchetgen, E. J. T.; Cornelis, M.; Kraft, P., Methodological challenges in Mendelian randomization, Epidemiology, 25, 427-435, (2014)
[60] Wang, L.; Tchetgen, E. T., Bounded, efficient and multiply robust estimation of average treatment effects using instrumental variables, arXiv preprint arXiv:1611.09925, (2018) · Zbl 1398.62348
[61] Zhang, J. L.; Rubin, D. B., Estimation of causal effects via principal stratification when some outcomes are truncated by “death”, Journal of Educational and Behavioral Statistics, 28, 353-368, (2003)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.