Efficient estimation for case‐cohort studies

作者: Bin Nan

DOI: 10.2307/3316024

关键词:

摘要: The author considers time-to-event data from case-cohort designs. As existing methods are either inefficient or based on restrictive assumptions concerning the censoring mechanism, he proposes a semi-parametrically efficient estimator under usual for Cox regression models. in question is obtained by one-step Newton-Raphson approximation that solves score equations with initial value an method. proves consistent, asymptotically and normally distributed limit. He also resorts to simulations show proposed performs well finite samples it considerably improves efficiency of pseudo-likelihood estimators when correlate missing covariate available. Although focuses situation where covariates discrete, explores how method can be applied models continuous covariates. L'auteur s'interesse des temps d'attente pour plans de type cas-cohorte. Comme les methodes existantes sont soit inefficaces, fondees sur postulats restrictifs concernant le mecanisme censure, il propose un estimateur semiparametriquement efficace sous conditions usuelles modeles Cox. L'estimateur en resulte d'une du premier ordre scores efficaces initialisees au moyen methode existante. L'auteur demontre que l'estimateur est convergent, asymptotiquement et loi limite normale. Il outre recours montrer se comporte bien taille finie qu'il s'avere beaucoup plus estimateurs pseudo-vraisemblance lorsque l'on dispose variable correlee avec une covariable manquante. Bien son attention porte principalement cas covariables discretes, l'auteur explique aussi comment la peut ětre appliquee aux continues.

参考文章(24)
James M. Robins, Andrea Rotnitzky, Recovery of Information and Adjustment for Dependent Censoring Using Surrogate Markers Birkhäuser, Boston, MA. pp. 297- 331 ,(1992) , 10.1007/978-1-4757-1229-2_14
A. W. van der Vaart, Asymptotic Statistics Cambridge University Press. ,(1998) , 10.1017/CBO9780511802256
David R. Cox, Regression Models and Life-Tables Springer Series in Statistics. ,vol. 34, pp. 527- 541 ,(1992) , 10.1007/978-1-4612-4380-9_37
Amy H Herring, Joseph G Ibrahim, Likelihood-Based Methods for Missing Covariates in the Cox Proportional Hazards Model Journal of the American Statistical Association. ,vol. 96, pp. 292- 302 ,(2001) , 10.1198/016214501750332866
O. Borgan, L. Goldstein, B. Langholz, Methods for the Analysis of Sampled Cohort Data in the Cox Proportional Hazards Model Annals of Statistics. ,vol. 23, pp. 1749- 1778 ,(1995) , 10.1214/AOS/1176324322
Jon A. Wellner, Mary J. Emond, Bin Nan, Information bounds for Cox regression models with missing data Annals of Statistics. ,vol. 32, pp. 723- 753 ,(2004) , 10.1214/009053604000000157
D. J. Thompson, D. G. Horvitz, A generalization of sampling without replacement from a finite universe. Journal of the American Statistical Association. ,vol. 47, pp. 663- 685 ,(1952) , 10.2307/2280784
Hua Yun Chen, Double-semiparametric method for missing covariates in Cox regression models Journal of the American Statistical Association. ,vol. 97, pp. 565- 576 ,(2002) , 10.1198/016214502760047096
Steven G. Self, Ross L. Prentice, Asymptotic Distribution Theory and Efficiency Results for Case-Cohort Studies Annals of Statistics. ,vol. 16, pp. 64- 81 ,(1988) , 10.1214/AOS/1176350691