Causal inference plays a crucial role in biomedical studies and social sciences. Over the years, researchers have devised various methods to facilitate causal inference, particularly in observational studies. Among these methods, the doubly robust estimator distinguishes itself through a remarkable feature: it retains its consistency even when only one of the two components – either the propensity score model or the outcome mean model – is correctly specified, rather than demanding correctness in both simultaneously. In this paper, we focus on scenarios where semiparametric models are employed for both the propensity score and the outcome mean. Semiparametric models offer a valuable blend of interpretability akin to parametric models and the adaptability characteristic of nonparametric models. In this context, achieving correct model specification involves both accurately specifying the unknown function and consistently estimating the unknown parameter. We introduce a novel concept: the relaxed doubly robust estimator. It operates in a manner reminiscent of the traditional doubly robust estimator but with a reduced requirement for double robustness. In essence, it only mandates the consistent estimate of the unknown parameter, without requiring the correct specification of the unknown function. This means that it only necessitates a partially correct model specification. We conduct a thorough analysis to establish the double robustness and semiparametric efficiency of our proposed estimator. Furthermore, we bolster our findings with comprehensive simulation studies to illustrate the practical implications of our approach.

References

• Bang, H., & Robins, J. M. (2005). Doubly robust estimation in missing data and causal inference models. Biometrics, 61(4), 962–973. https://doi.org/10.1111/biom.2005.61.issue-4
• Bickel, P. J., Klaassen, J., Ritov, Y., & Wellner, J. A. (1993). Efficient and adaptive estimation for semiparametric models. Johns Hopkins University Press Baltimore.
• Cheng, P. E. (1994). Nonparametric estimation of mean functionals with data missing at random. Journal of the American Statistical Association, 89(425), 81–87. https://doi.org/10.1080/01621459.1994.10476448
• Cook, R. D. (2009). Regression graphics: Ideas for studying regressions through graphics. John Wiley & Sons.
• Hahn, J. (1998). On the role of the propensity score in efficient semiparametric estimation of average treatment effects. Econometrica, 66(2), 315–331. https://doi.org/10.2307/2998560
• Hu, Z., Follmann, D. A., & Qin, J. (2012). Semiparametric double balancing score estimation for incomplete data with ignorable missingness. Journal of the American Statistical Association, 107(497), 247–257. https://doi.org/10.1080/01621459.2012.656009
• Ichimura, H. (1993). Semiparametric least squares (SLS) and weighted SLS estimation of single-index models. Journal of Econometrics, 58(1–2), 71–120. https://doi.org/10.1016/0304-4076(93)90114-K
• Imbens, G. W. (2004). Nonparametric estimation of average treatment effects under exogeneity: A review. Review of Economics and Statistics, 86(1), 4–29. https://doi.org/10.1162/003465304323023651
• Imbens, G. W., & Rubin, D. B. (2015). Causal inference in statistics, social, and biomedical sciences. Cambridge University Press.
• Klein, R. W., & Spady, R. H. (1993). An efficient semiparametric estimator for binary response models. Econometrica: Journal of the Econometric Society, 61(2), 387–421. https://doi.org/10.2307/2951556
• Li, K.-C. (1991). Sliced inverse regression for dimension reduction. Journal of the American Statistical Association, 86(414), 316–327. https://doi.org/10.1080/01621459.1991.10475035
• Lunceford, J. K., & Davidian, M. (2004). Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study. Statistics in Medicine, 23(19), 2937–2960. https://doi.org/10.1002/sim.v23:19
• Ma, Y., & Zhu, L. (2012). A semiparametric approach to dimension reduction. Journal of the American Statistical Association, 107(497), 168–179. https://doi.org/10.1080/01621459.2011.646925
• Ma, Y., & Zhu, L. (2013). A review on dimension reduction. International Statistical Review, 81(1), 134–150. https://doi.org/10.1111/insr.2013.81.issue-1
• Neyman, J. (1923). Sur les applications de la thar des probabilities aux experiences agaricales: Essay de principle. english translation of excerpts by Dabrowska, D. and Speed, T. Statistical Science, 5(4), 465–472.
• Robins, J. M., Rotnitzky, A., & Zhao, L. P. (1994). Estimation of regression coefficients when some regressors are not always observed. Journal of the American Statistical Association, 89(427), 846–866. https://doi.org/10.1080/01621459.1994.10476818
• Robins, J. M., Rotnitzky, A., & Zhao, L. P. (1995). Analysis of semiparametric regression models for repeated outcomes in the presence of missing data. Journal of the American Statistical Association, 90(429), 106–121. https://doi.org/10.1080/01621459.1995.10476493
• Rosenbaum, P. R. (2002). Overt bias in observational studies. Springer.
• Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41–55. https://doi.org/10.1093/biomet/70.1.41
• Rotnitzky, A., Robins, J. M., & D. O. Scharfstein (1998). Semiparametric regression for repeated outcomes with nonignorable nonresponse. Journal of the American Statistical Association, 93(444), 1321–1339. https://doi.org/10.1080/01621459.1998.10473795
• Rotnitzky, A., & Vansteelandt, S. (2014). Double-robust methods. In Handbook of Missing Data Methodology (pp. 185–212). CRC Press.
• Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5), 688–701. https://doi.org/10.1037/h0037350
• Rubin, D. B. (1980). Randomization analysis of experimental data: The fisher randomization test comment. Journal of the American Statistical Association, 75(371), 591–593.
• Scharfstein, D. O., Rotnitzky, A., & Robins, J. M. (1999). Adjusting for nonignorable drop-out using semiparametric nonresponse models. Journal of the American Statistical Association, 94(448), 1096–1120. https://doi.org/10.1080/01621459.1999.10473862
• Tsiatis, A. A. (2006). Semiparametric theory and missing data. Springer.

To cite this article: Tinghui Xu & Jiwei Zhao (2024) Relaxed doubly robust estimation in causal inference, Statistical Theory and Related Fields, 8:1, 69-79, DOI: 10.1080/24754269.2024.2313826

To link to this article: https://doi.org/10.1080/24754269.2024.2313826