On bootstrap accuracy with censored data
Kani Chen and Shaw-Hwa Lo
Source: Ann. Statist. Volume 24, Number 2
(1996), 569-595.
Abstract
In survival analysis with censored data, we consider three closely related survival function estimators: the Kaplan-Meier, Nelson and moment estimators. We derive the Edgeworth expansions for these three estimators with Studentization. Edgeworth expansions for the corresponding bootstrap statistics are also given. It is found that the bootstrap approximation is better than the normal approximation for the Studentized Kaplan-Meier and Nelson estimators, but not so for the Studentized moment estimator. With these results, we construct bootstrap-based confidence intervals with better coverage probabilities. We also include some simulations which show strong agreement with our theoretical findings.
First Page:
Show
Hide
Keywords: Kaplan-Meier estimator; Nelson estimator; moment estimator; Greenwood formula; Edgeworth expansion
Full-text: Open access
Links and Identifiers
Permanent link to this document: http://projecteuclid.org/euclid.aos/1032894453
Mathematical Reviews number (MathSciNet): MR1394976
Digital Object Identifier: doi:10.1214/aos/1032894453
Zentralblatt MATH identifier: 0860.62036
References
ABRAMOVITCH, L. and SINGH, K. 1985. Edgeworth corrected pivotal statistics and the bootstrap. Ann. Statist. 13 116 132. Z.
Mathematical Reviews (MathSciNet): MR86f:62031
Zentralblatt MATH: 0575.62018
Digital Object Identifier: doi:10.1214/aos/1176346580
Project Euclid: euclid.aos/1176346580
AKRITAS, M. G. 1986. Bootstrapping the Kaplan Meier estimator J. Amer. Statist. Assoc. 81 1032 1038. Z.
Mathematical Reviews (MathSciNet): MR867628
Zentralblatt MATH: 0635.62032
Digital Object Identifier: doi:10.2307/2289079
JSTOR: links.jstor.org
ALTSHULER, B. 1970. Theory for the measurement of competing risks in animal experiments. Math. Biosci. 6 1 11. Z.
Mathematical Reviews (MathSciNet): MR42:1301
Zentralblatt MATH: 0211.23503
Digital Object Identifier: doi:10.1016/0025-5564(70)90052-0
BICKEL, P. J., GOTZE, F. and VAN ZWET, W. R. 1986. The Edgeworth expansion for U-statistics of ¨ degree two. Ann. Statist. 14 1463 1484. Z.
BRESLOW, N. and CROWLEY, J. 1974. A large sample study of the life table and product-limit estimates under random censorship. Ann. Statist. 2 437 453. Z.
Mathematical Reviews (MathSciNet): MR56:16874
Zentralblatt MATH: 0283.62023
Digital Object Identifier: doi:10.1214/aos/1176342705
Project Euclid: euclid.aos/1176342705
CALLARET, H. and VERAVERBEKE, N. 1981. The order of the normal approximation for a Studentized U-statistic. Ann. Statist. 9 194 200. Z.
Mathematical Reviews (MathSciNet): MR600547
Zentralblatt MATH: 0457.62018
Digital Object Identifier: doi:10.1214/aos/1176345347
Project Euclid: euclid.aos/1176345347
CHEN, K. and YING, Z. 1996. A counterexample to a conjecture on Hall Wellner band. Ann. Statist. 24 641 646. Z.
Mathematical Reviews (MathSciNet): MR1394979
Zentralblatt MATH: 0859.62046
Digital Object Identifier: doi:10.1214/aos/1032894456
Project Euclid: euclid.aos/1032894456
CUZICK, J. 1985. Asy mptotic properties of censored linear rank tests. Ann. Statist. 13 133 141. Z.
Mathematical Reviews (MathSciNet): MR86d:62076
Zentralblatt MATH: 0584.62069
Digital Object Identifier: doi:10.1214/aos/1176346581
Project Euclid: euclid.aos/1176346581
EFRON, B. 1981. Censored data and the bootstrap. J. Amer. Statist. Assoc. 76 312 319. Z.
Mathematical Reviews (MathSciNet): MR82h:62066
Zentralblatt MATH: 0461.62039
Digital Object Identifier: doi:10.2307/2287832
GILL, R. D. 1983. Large sample behavior of the product-limit estimator on the whole line. Ann. Statist. 11 49 58. Z.
Mathematical Reviews (MathSciNet): MR684862
Zentralblatt MATH: 0518.62039
Digital Object Identifier: doi:10.1214/aos/1176346055
Project Euclid: euclid.aos/1176346055
GREENWOOD, M. 1926. The natural duration of cancer. In Report on Public Health and Medical Subjects 33 1 26. Her Majesty's Stationary Office, London. Z. Z.
HALL, P. 1988. Theoretical comparison of bootstrap confidence intervals with discussion. Ann. Statist. 16 927 981.
Mathematical Reviews (MathSciNet): MR959185
Zentralblatt MATH: 0663.62046
Digital Object Identifier: doi:10.1214/aos/1176350933
Project Euclid: euclid.aos/1176350933
HALL, P. 1992. The Bootstrap and Edgeworth Expansion. Springer, Berlin. Z.
Mathematical Reviews (MathSciNet): MR1145237
HALL, W. J. and WELLNER, J. A. 1980. Confidence bands for a survival curve from censored data. Biometrika 67 133 143. Z.
Zentralblatt MATH: 0423.62078
Mathematical Reviews (MathSciNet): MR570515
Digital Object Identifier: doi:10.1093/biomet/67.1.133
JSTOR: links.jstor.org
HELMERS, R. 1991. On the Edgeworth expansion and the bootstrap approximation for a Studentized U-statistic. Ann. Statist. 19 470 484. Z.
Mathematical Reviews (MathSciNet): MR92d:62020
Zentralblatt MATH: 0734.62049
Digital Object Identifier: doi:10.1214/aos/1176347994
Project Euclid: euclid.aos/1176347994
KAPLAN, E. L. and MEIER, P. 1958. Nonparametric estimation from incomplete observations. J. Amer. Statist. Assoc. 53 457 481. Z.
Zentralblatt MATH: 0089.14801
Mathematical Reviews (MathSciNet): MR93867
Digital Object Identifier: doi:10.2307/2281868
JSTOR: links.jstor.org
LO, S-H. and SINGH, K. 1986. The product-limit estimator and the bootstrap: some asy mptotic representations. Probab. Theory Related Fields 71 455 465. Z.
Mathematical Reviews (MathSciNet): MR87i:62081
Zentralblatt MATH: 0561.62032
Digital Object Identifier: doi:10.1007/BF01000216
PRENTICE, R. L. 1978. Linear rank tests with right censored data. Biometrika 65 167 179.
Mathematical Reviews (MathSciNet): MR80a:62060
Zentralblatt MATH: 0377.62024
Digital Object Identifier: doi:10.1093/biomet/65.1.167
JSTOR: links.jstor.org
KOWLOON, HONG KONG COLUMBIA UNIVERSITY
NEW YORK, NEW YORK 10027
