×

Empirical likelihood inference for the accelerated failure time model. (English) Zbl 1209.62091

Summary: Accelerated failure time (AFT) models are useful regression tools for studying the association between a survival time and covariates. Semiparametric inference procedures have been proposed in an extensive literature. Among these, use of an estimating equation which is monotone in the regression parameter and has some excellent properties was proposed by M. Fygenson and Y. Ritov [Ann. Stat. 22, No. 2, 732–746 (1994; Zbl 0807.62032)]. However, there is a serious under-coverage problem for small sample sizes. We derive the limiting distribution of the empirical log-likelihood ratio for the regression parameter on the basis of monotone estimating equations. Furthermore, the empirical likelihood (EL) confidence intervals/regions for the regression parameter are obtained. We conduct a simulation study in order to compare the proposed EL method with the normal approximation method. The simulation results suggest that the empirical likelihood based method outperforms the normal approximation based method in terms of coverage probability. Thus, the proposed EL method overcomes the under-coverage problem of the normal approximation method.

MSC:

62G08 Nonparametric regression and quantile regression
62G15 Nonparametric tolerance and confidence regions
65C60 Computational problems in statistics (MSC2010)

Citations:

Zbl 0807.62032

Software:

emplik
Full Text: DOI

References:

[1] Arvesen, J. N., Jackknifing \(U\)-statistics, Ann. Math. Statist., 40, 2076-2100 (1969) · Zbl 0193.16403
[2] Basawa, I. V.; Koul, H. L., Large-sample statistics based on quadratic dispersion, Int. Stat. Rev., 56, 199-219 (1980) · Zbl 0707.62064
[3] Billingsley, P., Probability and Measure (1986), John Wiley and Sons: John Wiley and Sons New York · Zbl 0649.60001
[4] Cox, D. R., Regression models and life-tables (with discussion), J. R. Stat. Soc. Ser. B, 34, 187-220 (1972) · Zbl 0243.62041
[5] Fygenson, M.; Ritov, Y., Monotone estimating equations for censored data, Ann. Statist., 22, 732-746 (1994) · Zbl 0807.62032
[6] Hoeffding, W., A class of statistics with asymptotically normal distribution, Ann. Math. Statist., 19, 293-325 (1948) · Zbl 0032.04101
[7] Jing, B. Y.; Yuan, J.; Zhou, W., Empirical likelihood for non-degenerate \(U\)-statistics, Statist. Probab. Lett., 78, 599-607 (2008) · Zbl 1137.62333
[8] Jing, B. Y.; Yuan, J.; Zhou, W., Jackknife empirical likelihood, J. Amer. Statist. Assoc., 104, 1224-1232 (2009) · Zbl 1388.62136
[9] Kirkpatrick, S.; Gelatt, C. D.; Vecchi, M., Optimization by simulated annealing, Science, 220, 671-680 (1983) · Zbl 1225.90162
[10] Koul, H.; Susarla, V.; van Ryzin, J., Regression analysis with randomly right-censored data, Ann. Statist., 9, 1276-1288 (1981) · Zbl 0477.62046
[11] Lai, T. L.; Ying, Z., Linear rank statistics in regression analysis with censored or truncated data, J. Multivariate Anal., 40, 13-45 (1992) · Zbl 0799.62071
[12] Lee, A. J., \(U\)-Statistics, Theory and Practice (1990), Marcel Dekker Inc.: Marcel Dekker Inc. New York · Zbl 0771.62001
[13] Li, G.; Wang, Q. H., Empirical likelihood regression analysis for right censored data, Statist. Sinica, 13, 51-68 (2003) · Zbl 1017.62093
[14] Lin, D. Y.; Geyer, C. J., Computational methods for semiparametric linear regression with censored data, J. Comput. Graph. Statist., 1, 77-90 (1992)
[15] Lin, D. Y.; Wei, L. J.; Ying, Z., Accelerated failure time models for counting processes, Biometrika, 85, 605-618 (1998) · Zbl 0947.62069
[16] Owen, A. B., Empirical likelihood ratio confidence intervals for a single functional, Biometrika, 75, 237-249 (1988) · Zbl 0641.62032
[17] Owen, A. B., Empirical likelihood and confidence regions, Ann. Statist., 18, 90-120 (1990) · Zbl 0712.62040
[18] Owen, A. B., Empirical Likelihood (2001), Chapman and Hall, CRC: Chapman and Hall, CRC New York · Zbl 0989.62019
[19] Parzen, M. I.; Wei, L. J.; Ying, Z., A resampling method based on pivotal estimating functions, Biometrika, 81, 341-350 (1994) · Zbl 0807.62038
[20] Qin, G.; Jing, B. Y., Empirical likelihood for censored linear regression, Scand. J. Statist., 28, 661-673 (2001) · Zbl 1010.62060
[21] Ritov, Y., Estimating regression parameters using linear rank tests for censored data, Ann. Statist., 18, 303-328 (1990) · Zbl 0713.62045
[22] Sen, P. K., On some convergence properties of \(U\)-statistics, Calcutta Statist. Assoc. Bull., 10, 1-18 (1960) · Zbl 0109.12504
[23] Serfling, R. J., Approximation Theorems of Mathematical Statistics (1980), John Wiley: John Wiley New York · Zbl 0423.60030
[24] Subramanian, S., Censored median regression and profile empirical likelihood, Stat. Methodol., 4, 493-503 (2007) · Zbl 1248.62059
[25] Tsiatis, A. A., Estimating regression parameters using linear rank tests for censored data, Ann. Statist., 18, 354-372 (1990) · Zbl 0701.62051
[26] Wei, L. J.; Ying, Z.; Lin, D. Y., Linear regression analysis of censored survival data based on rank tests, Biometrika, 77, 845-851 (1990)
[27] Wood, A. T.A.; Do, K. A.; Broom, B. M., Sequential linearization of empirical likelihood constraints with application to \(U\)-statistics, J. Comput. Graph. Statist., 5, 365-385 (1996)
[28] Ying, Z., A large sample study of rank estimation for censored regression data, Ann. Statist., 21, 76-99 (1993) · Zbl 0773.62048
[29] Zhao, Y.; Huang, Y., Test-based interval estimation under the accelerated failure time model, Comm. Statist. Simulation Comput., 36, 593-605 (2007) · Zbl 1121.62085
[30] Zhou, M., Empirical likelihood analysis of the rank estimator for the censored accelerated failure time model, Biometrika, 92, 492-498 (2005) · Zbl 1094.62127
[31] Zhou, M.; Li, G., Empirical likelihood analysis of the Buckley-James estimator, J. Multivariate Anal., 99, 649-664 (2008) · Zbl 1139.62025
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.