×

zbMATH — the first resource for mathematics

Robust estimation for the Cox regression model based on trimming. (English) Zbl 1404.62122
Summary: We propose a robust Cox regression model with outliers. The model is fit by trimming the smallest contributions to the partial likelihood. To do so, we implement a Metropolis-type maximization routine, and show its convergence to a global optimum. We discuss global robustness properties of the approach, which is illustrated and compared through simulations. We finally fit the model on an original and on a benchmark data set.

MSC:
62P10 Applications of statistics to biology and medical sciences; meta analysis
62J99 Linear inference, regression
Software:
coxrobust; R; robustbase
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Andersen, Cox regression model for counting processes: a large sample study, The Annals of Statistics 10 pp 1100– (1982) · Zbl 0526.62026 · doi:10.1214/aos/1176345976
[2] Andrews, Data: A Collection of Problems From Many Fields for the Student and Research Worker (1985) · Zbl 0567.62002
[3] Becker, The masking breakdown point of multivariate outliers, Journal of the American Statistical Association 94 pp 945– (1999) · Zbl 1072.62600 · doi:10.1080/01621459.1999.10474199
[4] Bednarski, On sensitivity of Cox’s estimator, Statistics and Decisions 7 pp 215– (1989) · Zbl 0675.62021
[5] Bednarski, Robust estimation in Cox regression model, Scandinavian Journal of Statistics 20 pp 213– (1993) · Zbl 0794.62026
[6] Bednarski, On a robust modification of Breslow’s cumulated hazard estimator, Computational Statistics and Data Analysis 52 pp 234– (2007) · Zbl 1452.62794 · doi:10.1016/j.csda.2006.12.003
[7] Bednarski, coxrobust: Robust Estimation in Cox Model (2006)
[8] Bednarski, Trimmed likelihood estimation of location and scale of the normal distribution, Australian Journal of Statistics 35 pp 141– (1993) · Zbl 0798.62043 · doi:10.1111/j.1467-842X.1993.tb01321.x
[9] Bednarski, Robustness and efficiency of Sasieni-type estimators in the Cox model, Journal of Statistical Planning and Inference 115 pp 261– (2003) · Zbl 1041.62028 · doi:10.1016/S0378-3758(02)00115-5
[10] Breslow, Covariance analysis of censored survival data, Biometrics 30 pp 89– (1974) · doi:10.2307/2529620
[11] Burr, A comparison of certain bootstrap confidence intervals in the Cox model, Journal of the American Statistical Association 89 pp 1290– (1994) · Zbl 0825.62423 · doi:10.1080/01621459.1994.10476869
[12] Cain, Approximate case influence for the proportional hazards regression model with censored data, Biometrics 40 pp 493– (1984) · doi:10.2307/2531402
[13] Cerioli, Error rates for multivariate outlier detection, Computational Statistics and Data Analysis 55 pp 544– (2011) · Zbl 1247.62192 · doi:10.1016/j.csda.2010.05.021
[14] Chakraborty, On an optimization problem in robust statistics, Journal of Computational and Graphical Statistics 17 pp 683– (2008) · doi:10.1198/106186008X340751
[15] Cholongitas, A systematic review of the performance of the model for end-stage liver disease (MELD) in the setting of liver transplantation, Liver Transplantation 12 pp 1049– (2006) · doi:10.1002/lt.20824
[16] Clarke, An adaptive method of estimation and outlier detection in regression applicable for small to moderate sample sizes, Probability and Statistics 20 pp 25– (2000) · Zbl 0971.62034
[17] Collett, Modelling Survival Data in Medical Research (2003)
[18] Cox, Regression models and life tables (with discussion), Journal of the Royal Statistical Society 34 pp 187– (1972) · Zbl 0243.62041
[19] Davison, Bootstrap Methods and their Applications (2006)
[20] Donoho, A Festschrift for Erich L. Lehmann (1983)
[21] Farcomeni, Robust double clustering: a method based on alternating concentration steps, Journal of Classification 26 pp 77– (2009) · Zbl 1276.62040 · doi:10.1007/s00357-009-9026-z
[22] Farcomeni, An overview of robust methods in medical research, Statistical Methods in Medical Research (2011)
[23] Grambsch, Proportional hazards tests and diagnostics based on weighted residuals, Biometrika 81 pp 515– (1994) · Zbl 0810.62096 · doi:10.1093/biomet/81.3.515
[24] Hampel, A general qualitative definition of robustness, Annals of Mathematical Statistics 42 pp 1887– (1971) · Zbl 0229.62041 · doi:10.1214/aoms/1177693054
[25] Hawkins, Identification of Outliers (1980) · Zbl 0438.62022 · doi:10.1007/978-94-015-3994-4
[26] Heritier, Robust Methods in Biostatistics (2009) · doi:10.1002/9780470740538
[27] Hodges , J. L. Jr. , 1967 Efficiency in normal samples and tolerance of extreme values for some estimates of location Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability 1 University of California Press
[28] Hubert, High-breakdown robust multivariate methods, Statistical Science 23 pp 92– (2008) · Zbl 1327.62328 · doi:10.1214/088342307000000087
[29] Kalbfleisch, The Statistical Analysis of the Failure Time Data (2002) · Zbl 1012.62104 · doi:10.1002/9781118032985
[30] Maronna, Robust Statistics: Theory and Methods (2006) · Zbl 1094.62040 · doi:10.1002/0470010940
[31] Minder, A robust method for proportional hazards regression, Statistics in Medicine 15 pp 1033– (1996) · doi:10.1002/(SICI)1097-0258(19960530)15:10<1033::AID-SIM215>3.0.CO;2-Y
[32] Nardi, New residuals for Cox regression and their application to outlier screening, Biometrics 55 pp 523– (1999) · Zbl 1059.62684 · doi:10.1111/j.0006-341X.1999.00523.x
[33] Ploner , M. Heinze , G. 2009 coxphw: Weighted Cox regression
[34] R Development Core Team, R: A Language and Environment for Statistical Computing (2009)
[35] Reid, Influence function for proportional hazards regression, Biometrika 72 pp 1– (1985) · doi:10.1093/biomet/72.1.1
[36] Riggio, Encephalopathy after transjugular intrahepatic portosystemic shunt with polytetrafluoroethylene-covered stent grafts, American Journal of Gastroenterology 103 pp 2738– (2008) · doi:10.1111/j.1572-0241.2008.02102.x
[37] Rousseeuw, A fast algorithm for the minimum covariance determinant estimator, Technometrics 41 pp 212– (1999) · doi:10.1080/00401706.1999.10485670
[38] Samuels , S. 1978 Robustness for survival estimators Ph.D. Thesis
[39] Sasieni, Maximum weighted partial likelihood estimates for the Cox model, Journal of the American Statistical Association 88 pp 144– (1993a) · Zbl 0771.62078 · doi:10.2307/2290707
[40] Sasieni, Some new estimators for Cox regression, Annals of Statistics 21 pp 1721– (1993b) · Zbl 0797.62020 · doi:10.1214/aos/1176349395
[41] Schemper, The estimation of average hazard ratios by weighted Cox regression, Statistics in Medicine 28 pp 2473– (2009) · doi:10.1002/sim.3623
[42] Schoenfeld, Partial residuals for the proportional hazards regression model, Biometrika 69 pp 239– (1982) · doi:10.1093/biomet/69.1.239
[43] Therneau, Martingale based residuals for survival models, Biometrika 77 pp 147– (1990) · Zbl 0692.62082 · doi:10.1093/biomet/77.1.147
[44] Valsecchi, Evaluation of long-term survival: use of diagnostics and robust estimators with Cox’s proportional hazards models, Statistics in Medicine 15 pp 2763– (1996) · doi:10.1002/(SICI)1097-0258(19961230)15:24<2763::AID-SIM319>3.0.CO;2-O
[45] Verweij, Cross-validation in survival analysis, Statistics in Medicine 12 pp 2305– (1993) · doi:10.1002/sim.4780122407
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.