Tags

Type your tag names separated by a space and hit enter

Global Partial Likelihood for Nonparametric Proportional Hazards Models.
J Am Stat Assoc 2010; 105(490):750-760JA

Abstract

As an alternative to the local partial likelihood method of Tibshirani and Hastie and Fan, Gijbels, and King, a global partial likelihood method is proposed to estimate the covariate effect in a nonparametric proportional hazards model, λ(t|x) = exp{ψ(x)}λ(0)(t). The estimator, ψ̂(x), reduces to the Cox partial likelihood estimator if the covariate is discrete. The estimator is shown to be consistent and semiparametrically efficient for linear functionals of ψ(x). Moreover, Breslow-type estimation of the cumulative baseline hazard function, using the proposed estimator ψ̂(x), is proved to be efficient. The asymptotic bias and variance are derived under regularity conditions. Computation of the estimator involves an iterative but simple algorithm. Extensive simulation studies provide evidence supporting the theory. The method is illustrated with the Stanford heart transplant data set. The proposed global approach is also extended to a partially linear proportional hazards model and found to provide efficient estimation of the slope parameter. This article has the supplementary materials online.

Authors+Show Affiliations

Department of Mathematics, HKUST, Kowloon, Hong Kong, China.No affiliation info availableNo affiliation info availableNo affiliation info available

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.

Language

eng

PubMed ID

22844168

Citation

Chen, Kani, et al. "Global Partial Likelihood for Nonparametric Proportional Hazards Models." Journal of the American Statistical Association, vol. 105, no. 490, 2010, pp. 750-760.
Chen K, Guo S, Sun L, et al. Global Partial Likelihood for Nonparametric Proportional Hazards Models. J Am Stat Assoc. 2010;105(490):750-760.
Chen, K., Guo, S., Sun, L., & Wang, J. L. (2010). Global Partial Likelihood for Nonparametric Proportional Hazards Models. Journal of the American Statistical Association, 105(490), pp. 750-760.
Chen K, et al. Global Partial Likelihood for Nonparametric Proportional Hazards Models. J Am Stat Assoc. 2010 01 1;105(490):750-760. PubMed PMID: 22844168.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Global Partial Likelihood for Nonparametric Proportional Hazards Models. AU - Chen,Kani, AU - Guo,Shaojun, AU - Sun,Liuquan, AU - Wang,Jane-Ling, Y1 - 2012/01/01/ PY - 2012/7/31/entrez PY - 2010/1/1/pubmed PY - 2010/1/1/medline SP - 750 EP - 760 JF - Journal of the American Statistical Association JO - J Am Stat Assoc VL - 105 IS - 490 N2 - As an alternative to the local partial likelihood method of Tibshirani and Hastie and Fan, Gijbels, and King, a global partial likelihood method is proposed to estimate the covariate effect in a nonparametric proportional hazards model, λ(t|x) = exp{ψ(x)}λ(0)(t). The estimator, ψ̂(x), reduces to the Cox partial likelihood estimator if the covariate is discrete. The estimator is shown to be consistent and semiparametrically efficient for linear functionals of ψ(x). Moreover, Breslow-type estimation of the cumulative baseline hazard function, using the proposed estimator ψ̂(x), is proved to be efficient. The asymptotic bias and variance are derived under regularity conditions. Computation of the estimator involves an iterative but simple algorithm. Extensive simulation studies provide evidence supporting the theory. The method is illustrated with the Stanford heart transplant data set. The proposed global approach is also extended to a partially linear proportional hazards model and found to provide efficient estimation of the slope parameter. This article has the supplementary materials online. SN - 0162-1459 UR - https://www.unboundmedicine.com/medline/citation/22844168/Global_Partial_Likelihood_for_Nonparametric_Proportional_Hazards_Models_ L2 - https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/22844168/ DB - PRIME DP - Unbound Medicine ER -