An alternative robust estimator of average treatment effect in causal inference. (English) Zbl 1414.62455
Summary: The problem of estimating the average treatment effects is important when evaluating the effectiveness of medical treatments or social intervention policies. Most of the existing methods for estimating the average treatment effect rely on some parametric assumptions about the propensity score model or the outcome regression model one way or the other. In reality, both models are prone to misspecification, which can have undue influence on the estimated average treatment effect. We propose an alternative robust approach to estimating the average treatment effect based on observational data in the challenging situation when neither a plausible parametric outcome model nor a reliable parametric propensity score model is available. Our estimator can be considered as a robust extension of the popular class of propensity score weighted estimators. This approach has the advantage of being robust, flexible, data adaptive, and it can handle many covariates simultaneously. Adopting a dimension reduction approach, we estimate the propensity score weights semiparametrically by using a non-parametric link function to relate the treatment assignment indicator to a low-dimensional structure of the covariates which are formed typically by several linear combinations of the covariates. We develop a class of consistent estimators for the average treatment effect and study their theoretical properties. We demonstrate the robust performance of the estimators on simulated data and a real data example of investigating the effect of maternal smoking on babies’ birth weight.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62G35 | Nonparametric robustness |
Keywords:
average treatment effects; causal inference; dimension reduction; efficient estimators; propensity score; robust estimationReferences:
| [1] | Almond, D., Chay, K. Y., and Lee, D. S. (2005). The costs of low birth weight. Quarterly Journal of Economics120, 1031-1083. |
| [2] | Bang, H. and Robins, J. M. (2005). Doubly robust estimation in missing data and causal inference models. Biometrics61, 962-973. · Zbl 1087.62121 |
| [3] | Benkeser, D. and Van Der Laan, M. (2016). The Highly Adaptive Lasso Estimator. In Data Science and Advanced Analytics (DSAA), 2016 IEEE International Conference on, 689-696. IEEE. |
| [4] | Bickel, P. J., Klaassen, C. A., Ritov, Y., and Wellner, J. A. (1993). Efficient and Adaptive Estimation for Semiparametric Models. Baltimore, MD: The Johns Hopkins University Press. · Zbl 0786.62001 |
| [5] | Cao, W., Tsiatis, A. A., and Davidian, M. (2009). Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data. Biometrika96, 723-734. · Zbl 1170.62007 |
| [6] | Carpenter, J. R., Kenward, M. G., and Vansteelandt, S. (2006). A comparison of multiple imputation and doubly robust estimation for analyses with missing data. Journal of the Royal Statistical Society, Series A (Statistics in Society)169, 571-584. |
| [7] | Cattaneo, M. D. (2010). Efficient semiparametric estimation of multi‐valued treatment effects under ignorability. Journal of Econometrics155, 138-154. · Zbl 1431.62109 |
| [8] | Chatterjee, N. and Carroll, R. J. (2005). Semiparametric maximum likelihood estimation in case‐control studies of gene‐environment interactions. Biometrika92, 399-418. · Zbl 1094.62136 |
| [9] | Cook, D. R. (1998). Regression Graphics: Ideas for Studying Regressions through Graphics. New York: Wiley. · Zbl 0903.62001 |
| [10] | Cook, D. R. and Weisberg, S. (1991). Discussion of sliced inverse regression for dimension reduction. Journal of the American Statistical Association86, 28-33. |
| [11] | De Luna, X., Waernbaum, I., and Richardson, T. (2011). Covariate selection for the nonparametric estimation of an average treatment effect. Biometrika98, 861-875. · Zbl 1228.62139 |
| [12] | Dong, Y. and Li, B. (2010). Dimension reduction for non‐elliptically distributed predictors: Second‐order moments. Biometrics97, 279-294. · Zbl 1233.62119 |
| [13] | Efron, B. (1988). Logistic regression, survival analysis, and the kaplan‐meier curve. Journal of the American Statistical Association83, 414-425. · Zbl 0644.62100 |
| [14] | Hahn, J. (1998). On the role of the propensity score in efficient semiparametric estimation of average treatment effects. Econometrica66, 315-331. · Zbl 1055.62572 |
| [15] | Härdle, W., Werwatz, A., Müller, M., and Sperlich, S. (2004). Nonparametric and Semiparametric Models. New York: Springer. · Zbl 1059.62032 |
| [16] | Hirano, K., Imbens, G. W., and Ridder, G. (2003). Efficient estimation of average treatment effects using the estimated propensity score. Econometrica71, 1161-1189. · Zbl 1152.62328 |
| [17] | Horvitz, D. G. and Thompson, D. J. (1952). A generalization of sampling without replacement from a finite universe. Journal of the American statistical Association47, 663-685. · Zbl 0047.38301 |
| [18] | Imai, K. and Ratkovic, M. (2014). Covariate balancing propensity score. Journal of the Royal Statistical Society, Series B (Statistical Methodology)76, 243-263. · Zbl 1411.62025 |
| [19] | Kang, J. D. and Schafer, J. L. (2007). Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. Statistical Science22, 523-539. · Zbl 1246.62073 |
| [20] | Koenker, R. and Yoon, J. (2009). Parametric links for binary choice models: A fisherian‐bayesian colloquy. Journal of Econometrics152, 120-130. · Zbl 1431.62313 |
| [21] | Lee, B. K., Lessler, J., and Stuart, E. A. (2010). Improving propensity score weighting using machine learning. Statistics in Medicine29, 337-346. |
| [22] | Li, B. and Dong, Y. (2009). Dimension reduction for non‐elliptically distributed predictors. The Annuals of Statistics37, 1272-1298. · Zbl 1160.62050 |
| [23] | Li, B. and Wang, S. (2007). On directional regression for dimension reduction. Journal of the American Statistical Association102, 997-1008. · Zbl 1469.62300 |
| [24] | Li, D., Wang, X., Lin, L., and Dey, D. K. (2016). Flexible link functions in nonparametric binary regression with gaussian process priors. Biometrics72, 707-719. · Zbl 1390.62063 |
| [25] | Li, K.‐C. (1991). Sliced inverse regression for dimension reduction. Journal of the American Statistical Association86, 316-327. · Zbl 0742.62044 |
| [26] | Lin, D. Y. and Zeng, D. (2009). Proper analysis of secondary phenotype data in case‐control association studies. Genetic Epidemiology33, 256-265. |
| [27] | Ma, Y. and Carroll, R. J. (2016). Semiparametric estimation in the secondary analysis of case-control studies. Journal of the Royal Statistical Society, Series B78, 127-151. · Zbl 1411.62326 |
| [28] | Ma, Y. and Zhu, L. (2012). A semiparametric approach to dimension reduction. Journal of the American Statistical Association107, 168-179. · Zbl 1261.62037 |
| [29] | Ma, Y. and Zhu, L. (2013). Efficient estimation in sufficient dimension reduction. The Annuals of Statistics41, 250-268. · Zbl 1347.62089 |
| [30] | McCaffrey, D. F., Ridgeway, G., and Morral, A. R. (2004). Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychological methods9, 403-425. |
| [31] | Neyman, J., Dabrowska, D. M., and Speed, T. P. (1990). On the application of probability theory to agricultural experiments: Essay on principles, section 9. Statistical Scince5, 465-480. |
| [32] | Petersen, M. L., Wang, Y., Van Der Laan, M. J., Guzman, D., Riley, E., and Bangsberg, D. R. (2007). Pillbox organizers are associated with improved adherence to hiv antiretroviral therapy and viral suppression: A marginal structural model analysis. Clinical Infectious Diseases45, 908-915. |
| [33] | Pregibon, D. (1980). Goodness of link tests for generalized linear models. Journal of the Royal Statistical Society, Series C29, 15-23. · Zbl 0434.62048 |
| [34] | Prentice, R. L. and Pyke, R. (1979). Logistic disease incidence models and case‐control studies. Biometrika66, 403-411. · Zbl 0428.62078 |
| [35] | Ridgeway, G. and McCaffrey, D. F. (2007). Comment: Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. Statistical Sciences22, 540-543. · Zbl 1246.62075 |
| [36] | Robins, J. M. and Rotnitzky, A. (2001). Comment on the bickel and kwon article, inference for semiparametric models: Some questions and an answer. Statistica Sinica11, 920-936. |
| [37] | Rosenbaum, P. R. and Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika70, 41-55. · Zbl 0522.62091 |
| [38] | Rotnitzky, A., Lei, Q., Sued, M., and Robins, J. M. (2012). Improved double‐robust estimation in missing data and causal inference models. Biometrika99, 439-456. · Zbl 1239.62071 |
| [39] | Rubin, D. (1974). Estimating causal effects of treatments in randomized and non‐randomized studies. Journal of Educational Psychology66, 688-701. |
| [40] | Rubin, D. B. (1976). Inference and missing data. Biometrika63, 581-592. · Zbl 0344.62034 |
| [41] | Rubin, D. B. (1986). Which ifs have causal answers. Journal of the American Statistical Association81, 961-962. |
| [42] | Rubin, D. B. and Little, R. A. (2002). Statistical Analysis with Missing Data (2nd ed.). New York: Wiley. · Zbl 1011.62004 |
| [43] | Rubin, D. B. and van der Laan, M. J. (2008). Empirical efficiency maximization: Improved locally efficient covariate adjustment in randomized experiments and survival analysis. The International Journal of Biostatistics4, Article-5. |
| [44] | Scharfstein, D. O., Rotnitzky, A., and Robins, J. M. (1999). Adjusting for nonignorable drop‐out using semiparametric nonresponse models. Journal of the American Statistical Association94, 1096-1120. · Zbl 1072.62644 |
| [45] | Tan, Z. (2006). A distributional approach for causal inference using propensity scores. Journal of the American Statistical Association101, 1619-1637. · Zbl 1171.62320 |
| [46] | Tan, Z. (2010). Bounded, efficient and doubly robust estimation with inverse weighting. Biometrika97, 661-682. · Zbl 1195.62037 |
| [47] | Tsiatis, A. (2006). Semiparametric Theory and Missing Data. New York: Springer. · Zbl 1105.62002 |
| [48] | van der Laan, M. (2015). A generally efficient targeted minimum loss based estimator. U.C. Berkeley Division of Biostatistics Working Paper Series. |
| [49] | van der Laan,M. J. (2014). Targeted estimation of nuisance parameters to obtain valid statistical inference. The International Journal of Biostatistics10, 29-57. |
| [50] | van der Laan, M. J. and Rose, S. (2011). Targeted Learning. New York: Springer. |
| [51] | van der Laan, M. J. and Rubin, D. (2006). Targeted maximum likelihood learning. The International Journal of Biostatistics2, 1-40. |
| [52] | Vansteelandt, S., Bekaert, M., and Claeskens, G. (2012). On model selection and model misspecification in causal inference. Statistical Methods in Medical Research21, 7-30. · Zbl 1365.62431 |
| [53] | Vermeulen, K. and Vansteelandt, S. (2015). Bias‐reduced doubly robust estimation. Journal of the American Statistical Association110, 1024-1036. · Zbl 1373.62218 |
| [54] | Vermeulen, K. and Vansteelandt, S. (2016). Data‐adaptive bias‐reduced doubly robust estimation. The International Journal of Biostatistics12, 253-282. |
| [55] | Wang, L., Rotnitzky, A., and Lin, X. (2010). Nonparametric regression with missing outcomes using weighted kernel estimating equations. Journal of the American Statistical Association105, 1135-1146. · Zbl 1390.62068 |
| [56] | Westreich, D., Lessler, J., and Funk, M. J. (2010). Propensity score estimation: Neural networks, support vector machines, decision trees (cart), and meta‐classifiers as alternatives to logistic regression. Journal of Clinical Epidemiology63, 826-833. |
| [57] | Xia, Y. C. (2007). A constructive approach to the estimation of dimension reduction directions. Annals of Statistics35, 2654-2690. · Zbl 1360.62196 |
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
