×

zbMATH — the first resource for mathematics

Inference for non-regular parameters in optimal dynamic treatment regimes. (English) Zbl 1365.62411
Summary: A dynamic treatment regime is a set of decision rules, one per stage, each taking a patient’s treatment and covariate history as input, and outputting a recommended treatment. In the estimation of the optimal dynamic treatment regime from longitudinal data, the treatment effect parameters at any stage prior to the last can be non-regular under certain distributions of the data. This results in biased estimates and invalid confidence intervals for the treatment effect parameters. In this article, we discuss both the problem of non-regularity, and available estimation methods. We provide an extensive simulation study to compare the estimators in terms of their ability to lead to valid confidence intervals under a variety of non-regular scenarios. Analysis of a data set from a smoking cessation trial is provided as an illustration.

MSC:
62P10 Applications of statistics to biology and medical sciences; meta analysis
62K05 Optimal statistical designs
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Collins LM, Prevention Science 5 pp 185– (2004) · doi:10.1023/B:PREV.0000037641.26017.00
[2] Lavori PW, Journal of the Royal Statistical Society 163 pp 29– (2000) · Zbl 04558314 · doi:10.1111/1467-985X.00154
[3] Lavori PW, Clinical Trials 1 pp 9– (2004) · doi:10.1191/1740774S04cn002oa
[4] Dawson R., Statistics in Medicine 23 pp 3249– (2004) · doi:10.1002/sim.1920
[5] Murphy SA, Statistics in Medicine 24 pp 1455– (2005) · doi:10.1002/sim.2022
[6] Schneider LS, American Journal of Geriatric Psychology 9 pp 346– (2001) · doi:10.1097/00019442-200111000-00004
[7] Rush AJ, Controlled Clinical Trials 25 pp 119– (2003) · doi:10.1016/S0197-2456(03)00112-0
[8] Thall PF, Statistics in Medicine 30 pp 1011– (2000) · doi:10.1002/(SICI)1097-0258(20000430)19:8<1011::AID-SIM414>3.0.CO;2-M
[9] Wahed AS, Biometrics 60 pp 124– (2004) · Zbl 1130.62388 · doi:10.1111/j.0006-341X.2004.00160.x
[10] Murphy SA, Journal of the Royal Statistical Society 65 pp 331– (2003) · Zbl 1065.62006 · doi:10.1111/1467-9868.00389
[11] Robins JM Optimal structural nested models for optimal sequential decisions . In Lin DY, Heagerty P, eds. Proceedings of the Second Seattle Symposium on Biostatistics. Springer, New York; 2004: 189-326. · Zbl 1279.62024 · doi:10.1007/978-1-4419-9076-1_11
[12] Moodie EEM, Biometrics 63 pp 447– (2007) · Zbl 1137.62077 · doi:10.1111/j.1541-0420.2006.00686.x
[13] Thall PF, Journal of the American Statistical Association 97 (457) pp 29– (2002) · Zbl 1073.62590 · doi:10.1198/016214502753479202
[14] Thall PF, Statistics in Medicine 26 pp 4687– (2007) · doi:10.1002/sim.2894
[15] Lunceford JK, Biometrics 58 pp 48– (2002) · Zbl 1209.62307 · doi:10.1111/j.0006-341X.2002.00048.x
[16] Wahed AS, Biometrika 93 (1) pp 163– (2006) · Zbl 1152.62397 · doi:10.1093/biomet/93.1.163
[17] Moodie EEM, To appear in Scandinavian Journal of Statistics (2008)
[18] Watkins Cjch., Learning from delayed rewards (1989)
[19] Sutton RS, Reinforcement learning: An introduction (1998)
[20] Murphy SA, Journal of Machine Learning Research 6 pp 1073– (2005)
[21] Bickel P., Efficient and adaptive estimation for semiparametric models (1993) · Zbl 0786.62001
[22] Shao J., Proceedings of the American Mathematical Society 122 (4) pp 1251– (1994) · Zbl 04525454 · doi:10.1090/S0002-9939-1994-1227529-8
[23] Andrews DWK., Econometrica 68 (2) pp 399– (2000) · Zbl 1015.62044 · doi:10.1111/1468-0262.00114
[24] Bickel P., Statistica Sinica 18 (3) pp 967– (2008)
[25] Hall P., Biometrika 82 pp 561– (1995) · Zbl 0830.62082 · doi:10.1093/biomet/82.3.561
[26] Donoho DL, Biometrika 81 (3) pp 425– (1994) · Zbl 0815.62019 · doi:10.1093/biomet/81.3.425
[27] Breiman L., Technometrics 37 (4) pp 373– (1995) · doi:10.1080/00401706.1995.10484371
[28] Gao H., Journal of Computational and Graphical Statistics 7 pp 469– (1998)
[29] Zou H., Journal of the American Statistical Association 101 (476) pp 1418– (2006) · Zbl 1171.62326 · doi:10.1198/016214506000000735
[30] Figueiredo M., IEEE Transactions on Image Processing 10 (9) pp 1322– (2001) · Zbl 1037.68775 · doi:10.1109/83.941856
[31] Cohen J., Statistical power for the behavioural sciences, 2. ed. (1988)
[32] Freedman B., The New England Journal of Medicine 317 (3) pp 141– (1987) · doi:10.1056/NEJM198707163170304
[33] Wu CFJ, Experiments: planning, analysis, and parameter design optimisation (2000)
[34] Davison AC, Bootstrap methods and their application (1997) · doi:10.1017/CBO9780511802843
[35] Nankervis JC, Computational Statistics & Data Analysis 49 pp 461– (2005) · Zbl 1429.62164 · doi:10.1016/j.csda.2004.05.023
[36] Strecher V., American Journal of Preventive Medicine 34 (5) pp 373– (2008) · doi:10.1016/j.amepre.2007.12.024
[37] Johnstone IM, The Annals of Statistics 32 (4) pp 1594– (2004) · Zbl 1047.62008 · doi:10.1214/009053604000000030
[38] Robins JM, Communications in Statistics 23 pp 2379– (1994) · Zbl 0825.62203 · doi:10.1080/03610929408831393
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.