The difference in restricted mean survival time has been increasingly used as an alternative measure to the hazard ratio in survival analysis. Although some statistical methods have been developed for estimating the difference in restricted mean survival time adjusted for measured confounders in observational studies, the impact of unmeasured confounding on the estimate has rarely been assessed. We develop a novel sensitivity analysis for the estimate of the difference in restricted mean survival time with respect to unmeasured confounding. After formulating the sensitivity analysis problem as an optimization problem, we explain how to obtain the sensitivity range of the difference in restricted mean survival time efficiently and assess its uncertainty using the percentile bootstrap confidence interval. Analytic results are provided for some important survival settings. Simulation studies show that the proposed methods perform well in various settings. We illustrate the proposed sensitivity analysis method by analyzing data from the German Breast Cancer Study Group study.
CornfieldJHaenszelWHammondEC, et al. Smoking and lung cancer: recent evidence and a discussion of some questions. J Natl Cancer Inst1959; 22: 173–203.
4.
LinDYPsatyBMKronmalRA. Assessing the sensitivity of regression results to unmeasured confounders in observational studies. Biometrics1998; 54: 948–963.
5.
RobinsJM. Association, causation, and marginal structural models. Synthese1999; 121: 151–179.
6.
BrumbackBAHernánMAHaneuseSJ, et al. Sensitivity analyses for unmeasured confounding assuming a marginal structural model for repeated measures. Stat Med2004; 23: 749–767.
7.
RosenbaumPR. Overt bias in observational studies. In: Observational Studies. New York: Springer, 2002, pp.71–104.
8.
ZhaoQSmallDSBhattacharyaBB. Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrap. J R Stat Soc Ser B: Stat Methodol2019; 81: 735–761.
9.
TanZ. A distributional approach for causal inference using propensity scores. J Am Stat Assoc2006; 101: 1619–1637.
10.
KlungsøyrOSextonJSandangerI, et al. Sensitivity analysis for unmeasured confounding in a marginal structural Cox proportional hazards model. Lifetime Data Anal2009; 15: 278–294.
11.
LinNXLoganSHenleyWE. Bias and sensitivity analysis when estimating treatment effects from the Cox model with omitted covariates. Biometrics2013; 69: 850–860.
12.
HuangRXuRDulaiPS. Sensitivity analysis of treatment effect to unmeasured confounding in observational studies with survival and competing risks outcomes. Stat Med2020; 39: 3397–3411.
13.
HernánMA. The hazards of hazard ratios. Epidemiology2010; 21: 13–15.
14.
RoystonPParmarMK. Restricted mean survival time: an alternative to the hazard ratio for the design and analysis of randomized trials with a time-to-event outcome. BMC Med Res Methodol2013; 13: 1–15.
15.
TrinquartLJacotJConnerSC, et al. Comparison of treatment effects measured by the hazard ratio and by the ratio of restricted mean survival times in oncology randomized controlled trials. J Clin Oncol2016; 34: 1813–1819.
16.
PakKUnoHKimDHet al. Interpretability of cancer clinical trial results using restricted mean survival time as an alternative to the hazard ratio. JAMA Oncol2017; 3: 1692–1696.
17.
HanKJungI. Restricted mean survival time for survival analysis: a quick guide for clinical researchers. Korean J Radiol2022; 23: 495–499.
18.
RoystonPParmarMK. The use of restricted mean survival time to estimate the treatment effect in randomized clinical trials when the proportional hazards assumption is in doubt. Stat Med2011; 30: 2409–2421.
19.
ColeSRHernánMA. Adjusted survival curves with inverse probability weights. Comput Methods Programs Biomed2004; 75: 45–49.
20.
XieJLiuC. Adjusted Kaplan–Meier estimator and log-rank test with inverse probability of treatment weighting for survival data. Stat Med2005; 24: 3089–3110.
21.
AndersenPKHansenMGKleinJP. Regression analysis of restricted mean survival time based on pseudo-observations. Lifetime Data Anal2004; 10: 335–350.
22.
TianLZhaoLWeiL. Predicting the restricted mean event time with the subject’s baseline covariates in survival analysis. Biostatistics2014; 15: 222–233.
23.
LewisD. Counterfactuals. Cambridge, MA: Harvard University Press, 1973.
24.
KleinJPMoeschbergerML. Survival Analysis: techniques for Censored and Truncated Data. New York: Springer, 2003.
25.
GreenlandSRobinsJM. Identifiability, exchangeability, and epidemiological confounding. Int J Epidemiol1986; 15: 413–419.
26.
WestreichDColeSR. Invited commentary: positivity in practice. Am J Epidemiol2010; 171: 674–677.
27.
IrwinJO. The standard error of an estimate of expectation of life, with special reference to expectation of tumourless life in experiments with mice. J Hyg (Lond)1949; 47: 188–189.
28.
ChenPYTsiatisAA. Causal inference on the difference of the restricted mean lifetime between two groups. Biometrics2001; 57: 1030–1038.
29.
KaplanELMeierP. Nonparametric estimation from incomplete observations. J Am Stat Assoc1958; 53: 457–481.
30.
BajalinovEB. Linear-Fractional Programming Theory, Methods, Applications and Software. Dordrecht: Springer Science & Business Media, 2003.
31.
CharnesACooperWW. Programming with linear fractional functionals. Nav Res Logist1962; 9: 181–186.
32.
ByrdRHLuPNocedalJ, et al. A limited memory algorithm for bound constrained optimization. SIAM J Sci Comput1995; 16: 1190–1208.
33.
R Development Core Team. R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing, 2021.
34.
BenderRAugustinTBlettnerM. Generating survival times to simulate Cox proportional hazards models. Stat Med2005; 24: 1713–1723.
35.
ColeMPJonesCTToddID. A new anti-oestrogenic agent in late breast cancer: an early clinical appraisal of ICI46474. Br J Cancer1971; 25: 270–275.
36.
SchumacherMBastertGBojarHet al. Randomized 2 2 trial evaluating hormonal treatment and the duration of chemotherapy in node-positive breast cancer patients. J Clin Oncol1994; 12: 2086–2093.
SauerbreiWRoystonPBojarH, et al. Modelling the effects of standard prognostic factors in node-positive breast cancer. German Breast Cancer Study Group (GBSG). Br J Cancer1999; 79: 1752–1760.
39.
ThomsonCSHoleDJTwelvesCJ, et al. Prognostic factors in women with breast cancer: distribution by socioeconomic status and effect on differences in survival. J Epidemiol Community Health2001; 55: 308–315.
40.
JangRWCaraiscosVBSwamiNet al. Simple prognostic model for patients with advanced cancer based on performance status. J Oncol Pract2014; 10: e335–e341.
41.
Early Breast Cancer Trialists’ Collaborative Group. Tamoxifen for early breast cancer: an overview of the randomised trials. Lancet1998; 351: 1451–1467.
42.
ConnerSCSullivanLMBenjaminEJ, et al. Adjusted restricted mean survival times in observational studies. Stat Med2019; 38: 3832–3860.
43.
RobinsJMRotnitzkyAScharfsteinDO. Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models. In: Statistical Models in Epidemiology, the Environment, and Clinical Trials. New York: Springer, 2000, pp.1–94.
44.
ColeSRHernánMA. Constructing inverse probability weights for marginal structural models. Am J Epidemiol2008; 168: 656–664.
45.
BaiXTsiatisAAO’BrienSM. Doubly-robust estimators of treatment-specific survival distributions in observational studies with stratified sampling. Biometrics2013; 69: 830–839.
46.
HastieTTibshiraniRFriedmanJH. Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York: Springer, 2009.
47.
van der LaanMJRoseS. Targeted Learning: Causal Inference for Observational and Experimental Data. New York: Springer, 2011.
48.
ChernozhukovVChetverikovDDemirerMet al. Double/debiased machine learning for treatment and structural parameters. Econom J2018; 21: C1–C68.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
