Nonparametric confidence intervals for the ratio of marginal hazard rates of paired survival times. (English) Zbl 1242.62119
Summary: Paired survival times with potential censoring are often observed from two treatment groups in clinical trials and other types of clinical studies. The ratio of marginal hazard rates may be used to quantify the treatment effects in these studies. In this paper, a nonparametric kernel method proposed by D. Tu [Biometric J. 3, 474–483 (2007)] is used to estimate the marginal hazard rate, and the method of variance estimates recovery (MOVER) is used for the construction of the confidence intervals of a time-dependent hazard ratio based on the confidence limits of a single marginal hazard rate. Two methods are proposed: one uses the delta method and another adopts the transformation method to construct confidence limits for the marginal hazard rate. Simulations are performed to evaluate the performance of the proposed methods. Real data from two clinical trials are analyzed using the proposed methods.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62N01 | Censored data models |
| 62N02 | Estimation in survival analysis and censored data |
| 62Q05 | Statistical tables |
| 65C60 | Computational problems in statistics (MSC2010) |
References:
| [1] | Batchelor, HL-A matching in treatment of burned patients with skin allografts, Lancet 2 pp 581– (1970) · doi:10.1016/S0140-6736(70)90165-0 |
| [2] | Bickel, On some global estimate of the deviations of density estimation, Annals of Statistics 1 pp 1071– (1993) · Zbl 0275.62033 · doi:10.1214/aos/1176342558 |
| [3] | Cai, Semiparametric mixed-effects models for clustered failure time data, Journal of the American Statistical Association 97 pp 514– (2002) · Zbl 1073.62569 · doi:10.1198/016214502760047041 |
| [4] | Cai, Estimating equations for hazard ratio parameters based on correlated failure time data, Biometrika 82 pp 151– (1995) · Zbl 0823.62084 · doi:10.1093/biomet/82.1.151 |
| [5] | Cao, Relative hazard rate estimation for right censored and left trucated data, Test 14 pp 257– (2005) · Zbl 1069.62078 · doi:10.1007/BF02595406 |
| [6] | Cheng, Confidence bands for hazard rate under random censorship, Biometrika 93 pp 357– (2006) · Zbl 1153.62360 · doi:10.1093/biomet/93.2.357 |
| [7] | Cheng, Confidence intervals for the first crossing point of two hazard functions, Lifetime Data Analysis 15 pp 441– (2009) · Zbl 1322.62265 · doi:10.1007/s10985-009-9132-6 |
| [8] | Dallas, Testing equality of survival functions based on both paired and unpaired censored data, Biometrics 56 pp 154– (2000) · Zbl 1060.62593 · doi:10.1111/j.0006-341X.2000.00154.x |
| [9] | Gilbert, Simultaneous inferences on the contrast of two hazard functions with censored observations, Biometrics 58 pp 773– (2002) · Zbl 1210.62162 · doi:10.1111/j.0006-341X.2002.00773.x |
| [10] | Hall, Empirical likelihood confidence bands in density estimation, Journal of Computational and Graphical Statistics 2 pp 273– (1993) · doi:10.2307/1390646 |
| [11] | Hougaard, Frailty models for survival data, Lifetime Data Analysis 1 pp 255– (1995) · doi:10.1007/BF00985760 |
| [12] | Huster, Modelling paired survival data with covariates, Biometrics 45 pp 145– (1989) · Zbl 0715.62224 · doi:10.2307/2532041 |
| [13] | Jones, Linear signed-rank tests for paired survival data subject to a common censoring time, Lifetime Data Analysis 11 pp 351– (2005) · Zbl 1099.62117 · doi:10.1007/s10985-005-2967-6 |
| [14] | Jung, Rank tests for matched survival data, Lifetime Data Analysis 5 pp 67– (1999) · Zbl 0924.62116 · doi:10.1023/A:1009635201363 |
| [15] | Jung, Non-parametric estimation for the difference of ratio of median failure times for paired observations, Statistics in medicine 14 pp 275– (1995) · doi:10.1002/sim.4780140306 |
| [16] | Lee, Survival Analysis: State of the Art pp 237– (1992) · doi:10.1007/978-94-015-7983-4_14 |
| [17] | Lee, Linear regression analysis for highly stratified failure time data, Journal American Statistial Association 88 pp 557– (1993) · Zbl 0775.62171 · doi:10.2307/2290336 |
| [18] | Liang, Modelling marginal hazards in multivariate failure time data, Journal Royal Statistical Scoiety B 55 pp 441– (1993) · Zbl 0783.62093 |
| [19] | Lin, Linear regression analysis for multivariate failure time observations, Journal of American Statistical Association 87 pp 1091– (1992) · Zbl 0850.62519 · doi:10.2307/2290646 |
| [20] | Mick, Phase II clinical trial design for noncytotoxic anticancer agents for which time to disease progression is the primary endpoint, Controlled Clinical Trials 21 pp 343– (2000) · doi:10.1016/S0197-2456(00)00058-1 |
| [21] | Nelsen, An Introduction to Copulas (2006) · Zbl 1152.62030 |
| [22] | Oakes, Bivariate survival models induced by frailties, Journal of the American Statistical Association 84 pp 487– (1989) · Zbl 0677.62094 · doi:10.2307/2289934 |
| [23] | Oakes, Combining stratified and unstratified log-rank tests in paired survival data, Statistics in Medicine 29 pp 1735– (2010) · doi:10.1002/sim.3921 |
| [24] | O’Brien, A paired Prentice-Wilcoxon test for censored paired data, Biometrics 43 pp 169– (1987) · doi:10.2307/2531957 |
| [25] | Parner, Asymptotic theory for the correlated gamma-frailty model, Annals of Statistics 26 pp 183– (1998) · Zbl 0934.62101 · doi:10.1214/aos/1030563982 |
| [26] | Ramasundarahettige, Confidence interval construction for a difference between two dependent intraclass correlation coefficients, Statistics in Medicine 28 pp 1041– (2009) · doi:10.1002/sim.3523 |
| [27] | Scott, The estimation of the hazard ratio in clinical trials and in meta-analysis, Mathematical Scientist 25 pp 54– (2000) · Zbl 0953.62117 |
| [28] | Shih, Assessing gamma frailty models for clustered failure time data, Lifetime Data Analysis 1 pp 205– (1995) · Zbl 0836.62097 · doi:10.1007/BF00985771 |
| [29] | Singer, Letter to the editor: construction of confidence limits about effect measures: a general approach, Statistics in Medicine 29 pp 1757– (2010) · doi:10.1002/sim.3887 |
| [30] | Tang, Confidence intervals for a difference between proportions based on paired data, Statistics in Medicine 29 pp 86– (2010) |
| [31] | Tanner, The estimation of the hazard function from randomly censored data by the kernel method, Annals of Statistics 11 pp 989– (1983) · Zbl 0546.62017 · doi:10.1214/aos/1176346265 |
| [32] | Tu, Under-smoothed kernel confidence intervals for the hazard ratio based on censored data, Biometrical Journal 3 pp 474– (2007) · doi:10.1002/bimj.200610323 |
| [33] | Wei, A generalized Gehan and Gilbert test for paired observations that are subject to arbitrary right censorship, Journal of the American Statistical Association 75 pp 634– (1980) · Zbl 0455.62032 · doi:10.2307/2287660 |
| [34] | Wei, Regression analysis of multivariate incomplete failure time data by modeling marginal distributions, Journal of the American Statistical Association 84 pp 1065– (1989) · doi:10.2307/2290084 |
| [35] | Woolson, Rank tests for censored matched pairs, Biometrika 67 pp 597– (1980) · Zbl 0445.62062 · doi:10.1093/biomet/67.3.597 |
| [36] | Xie, Bivariate frailty model for the analysis of multivariate survival time, Lifetime Data Analysis 2 pp 277– (1996) · Zbl 0862.62085 · doi:10.1007/BF00128978 |
| [37] | Yan, Enjoy the joy of copulas: with a package copula, Journal of Statistical Software 21 pp 1– (2007) · doi:10.18637/jss.v021.i04 |
| [38] | Yandell, Nonparametric inference for rates with censored survival data, Annals of Statistics 11 pp 1119– (1983) · Zbl 0598.62050 · doi:10.1214/aos/1176346326 |
| [39] | Zeng, Semiparametric transformation models with random effects for clustered failure time data, Statistica Sinica 18 pp 355– (2008) · Zbl 1137.62019 |
| [40] | Zou, Construction of confidence limits about effect measures: a general approach, Statistics in Medicine 27 pp 1693– (2008) · doi:10.1002/sim.3095 |
| [41] | Zou, Construction of confidence limits about effect measures: A general approach-reply, Statistics in Medicine 29 pp 1760– (2010) · doi:10.1002/sim.3909 |
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.
