×

zbMATH — the first resource for mathematics

On testing conditional qualitative treatment effects. (English) Zbl 1427.62134
This paper deals with hypothesis testing regarding the optimal treatment regime. Therefore, the authors introduce the notion of a conditional qualitative treatment effect (CQTE) and derive several helpful equivalent formulations for the null hypothesis that there is no CQTE. Based on kernel density estimations, they derive novel testing procedures for this problem and prove that the theoretical level is asymptotically kept. In case of specific alternatives, also asymptotic expansions of the power are given. The proposed method is illustrated in a simulation study and on real world data.
MSC:
62P10 Applications of statistics to biology and medical sciences; meta analysis
62G08 Nonparametric regression and quantile regression
62G10 Nonparametric hypothesis testing
62G07 Density estimation
Software:
KernSmooth
PDF BibTeX XML Cite
Full Text: DOI Euclid
References:
[1] Andrews, D. W. K. and Shi, X. (2013). Inference based on conditional moment inequalities. Econometrica81 609-666. · Zbl 1274.62311
[2] Andrews, D. W. K. and Shi, X. (2014). Nonparametric inference based on conditional moment inequalities. J. Econometrics179 31-45. · Zbl 1293.62065
[3] Armstrong, T. B. and Chan, H. P. (2016). Multiscale adaptive inference on conditional moment inequalities. J. Econometrics194 24-43. · Zbl 1431.62181
[4] Chakraborty, B., Murphy, S. and Strecher, V. (2010). Inference for non-regular parameters in optimal dynamic treatment regimes. Stat. Methods Med. Res.19 317-343. · Zbl 1365.62411
[5] Chang, M., Lee, S. and Whang, Y.-J. (2015). Nonparametric tests of conditional treatment effects with an application to single-sex schooling on academic achievements. Econom. J.18 307-346.
[6] Chernozhukov, V., Lee, S. and Rosen, A. M. (2013). Intersection bounds: Estimation and inference. Econometrica81 667-737. · Zbl 1274.62233
[7] Fan, J. and Li, R. (2001). Variable selection via nonconcave penalized likelihood and its oracle properties. J. Amer. Statist. Assoc.96 1348-1360. · Zbl 1073.62547
[8] Fan, A., Lu, W. and Song, R. (2016). Sequential advantage selection for optimal treatment regime. Ann. Appl. Stat.10 32-53. · Zbl 06586135
[9] Fan, C., Lu, W., Song, R. and Zhou, Y. (2017). Concordance-assisted learning for estimating optimal individualized treatment regimes. J. R. Stat. Soc. Ser. B. Stat. Methodol.79 1565-1582. · Zbl 1381.62097
[10] Giné, E., Mason, D. M. and Zaitsev, A. Yu. (2003). The \(L_{1}\)-norm density estimator process. Ann. Probab.31 719-768. · Zbl 1031.62026
[11] Gunter, L., Zhu, J. and Murphy, S. A. (2011). Variable selection for qualitative interactions. Stat. Methodol.8 42-55.
[12] Hsu, Y.-C. (2017). Consistent test for conditional treatment effects. Econom. J.20 1-22.
[13] Li, K.-C. and Duan, N. (1989). Regression analysis under link violation. Ann. Statist.17 1009-1052. · Zbl 0753.62041
[14] Lu, W., Zhang, H. H. and Zeng, D. (2013). Variable selection for optimal treatment decision. Stat. Methods Med. Res.22 493-504.
[15] Luedtke, A. R. and van der Laan, M. J. (2016). Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy. Ann. Statist.44 713-742. · Zbl 1338.62089
[16] Mason, D. M. and Polonik, W. (2009). Asymptotic normality of plug-in level set estimates. Ann. Appl. Probab.19 1108-1142. · Zbl 1180.62048
[17] Murphy, S. A. (2003). Optimal dynamic treatment regimes. J. R. Stat. Soc. Ser. B. Stat. Methodol.65 331-366. · Zbl 1065.62006
[18] Qian, M. and Murphy, S. A. (2011). Performance guarantees for individualized treatment rules. Ann. Statist.39 1180-1210. · Zbl 1216.62178
[19] Robins, J. M., Hernan, M. A. and Brumback, B. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology11 550-560.
[20] Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and non-randomized studies. J. Educ. Psychol.66 688-701.
[21] Shergin, V. V. (1990). The central limit theorem for finitely dependent random variables. In Probability Theory and Mathematical Statistics, Vol. II (Vilnius, 1989) 424-431. Mokslas, Vilnius.
[22] Shi, C., Song, R. and Lu, W. (2019). Supplement to “On testing conditional qualitative treatment effects.” DOI:10.1214/18-AOS1750SUPP.
[23] Wand, M. P. and Jones, M. C. (1993). Comparison of smoothing parameterizations in bivariate kernel density estimation. J. Amer. Statist. Assoc.88 520-528. · Zbl 0775.62105
[24] Wang, H. (2009). Forward regression for ultra-high dimensional variable screening. J. Amer. Statist. Assoc.104 1512-1524. · Zbl 1205.62103
[25] Watkins, C. J. C. H. and Dayan, P. (1992). Q-learning. Mach. Learn.8 279-292. · Zbl 0773.68062
[26] White, H. (1982). Maximum likelihood estimation of misspecified models. Econometrica50 1-25. · Zbl 0478.62088
[27] Zhang, B., Tsiatis, A. A., Laber, E. B. and Davidian, M. (2012). A robust method for estimating optimal treatment regimes. Biometrics68 1010-1018. · Zbl 1258.62116
[28] Zhang, B., Tsiatis, A. A., Laber, E. B. and Davidian, M. (2013). Robust estimation of optimal dynamic treatment regimes for sequential treatment decisions. Biometrika100 681-694. · Zbl 1284.62508
[29] Zhang, Y., Laber, E. B., Tsiatis, A. and Davidian, M. (2015). Using decision lists to construct interpretable and parsimonious treatment regimes. Biometrics71 895-904. · Zbl 1419.62490
[30] Zhang, Y., Laber, E. B., Tsiatis, A. and Davidian, M. (2016). Interpretable dynamic treatment regimes. Preprint. Available at arXiv:1606.01472. · Zbl 1409.62231
[31] Zhao, Y., Zeng, D., Rush, A. J. and Kosorok, M. R. (2012). Estimating individualized treatment rules using outcome weighted learning. J. Amer. Statist. Assoc.107 1106-1118. · Zbl 1443.62396
[32] Zhao, Y.-Q., Zeng, D., Laber, E. B. and Kosorok, M. R. (2015). New statistical learning methods for estimating optimal dynamic treatment regimes. J. Amer. Statist. Assoc.110 583-598. · Zbl 1373.62557
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.