On the Local and Stratified Likelihood Approaches in Single-Index Hazards Model

Abstract

We propose the single-index hazards model for censored survival data. As an extension of the Cox model and many transformation models, this model allows nonparametric modeling of covariate effects in a parsimonious way via a single index. In addition, the relative importance of covariates can be assessed via this model. We consider two commonly used profile likelihood methods for parameter estimation: the local profile likelihood method and the stratified profile likelihood method. It is shown that both methods may give consistent estimators under certain restrictive conditions, but in general they can yield biased estimation. Simulation studies are also conducted to demonstrate these bias phenomena. The existence and nature of the failures of these two commonly used approaches is somewhat surprising.

Keywords

Bias analysis / Cox model / Local likelihood / Profile likelihood / Single-index / Stratification

References

[1] Andersen P.K., Borgan Ø., Gill R.D., Keiding N. Statistical Models Based on Counting Processes. 1993 New York: Springer

[2] Andersen P.K., Gill R.D. Cox’s regression model for counting processes: a large sample study. Ann. Stat.. 1982, 10 1100-1120

[3] Bennett S. Analysis of survival data by the proportional odds model. Stat. Med.. 1983, 2 273-277

[4] Carroll R.J., Fan J., Gijbels I., Wand M.P. Generalized partially linear single-index models. J. Am. Stat. Assoc.. 1997, 92 477-489

[5] Chow T., Kereiakes D.J., Bartone C., Booth T., Schloss E.J., Waller T., Chung E.S., Menon S., Nallamothu B.K., Chan P.S. Prognostic utility of microvolt t-wave alternans in risk stratification of patients with ischemic cardiomyopathy. J. Am. Coll. Cardiol.. 2006, 47 1820-1827

[6] Cox D.R. Regression models and life tables (with discussion). J. R. Stat. Soc. B. 1972, 34 187-220

[7] Cox D.R. Partial likelihood. Biometrika. 1975, 62 269-276

[8] Cox D.R., Oakes D. Analysis of Survival Data. 1984 London: Chapman & Hall

[9] Dvoretzky A., Kiefer J., Wolfowitz J. Asymptotic minimax character of the sample distribution function and of the classical multinomial estimator. Ann. Math. Stat.. 1956, 27 642-669

[10] Fan J., Gijbels I., King M. Local likelihood and local partial likelihood in hazard regression. Ann. Stat.. 1997, 25 1661-1690

[11] Fleming T.R., Harrington D.P. Counting Processes and Survival Analysis. 1991 New York: Wiley

[12] Härdle W., Hall P., Ichimura H. Optimal smoothing in single-index models. Ann. Stat.. 1993, 21 157-178

[13] Kosorok M.R. Introduction to Empirical Processes and Semiparametric Inference. 2008 New York: Springer

[14] Kosorok M.R., Lee B.L., Fine J.P. Robust inference for univariate proportional hazards frailty regression models. Ann. Stat.. 2004, 32 1448-1491

[15] Motzer R.J., Mazumdar M., Bacik J., Berg W., Amsterdam A., Ferrara J. Survival and prognostic stratification of 670 patients with advanced renal cell carcinoma. J. Clin. Oncol.. 1999, 17 2530-2540

[16] Nielsen J.P., Linton O.B. Kernel estimation in a nonparametric marker dependent hazard model. Ann. Stat.. 1995, 23 1735-1748

[17] Pettitt A.N. Proportional odds models for survival data and estimates using ranks. Appl. Stat.. 1984, 33 169-175

[18] Yu Y., Ruppert D. Penalized spline estimation for partially linear single-index models. J. Am. Stat. Assoc.. 2002, 97 1042-1054

[19] Zeng D., Lin D.Y. Maximum likelihood estimation in semiparametric regression models with censored data (with discussion). J. R. Stat. Soc. B. 2007, 69 507-564