Weighted local polynomial estimations of a non-parametric function with censoring indicators missing at random and their applications

Abstract

In this paper, we consider the weighted local polynomial calibration estimation and imputation estimation of a non-parametric function when the data are right censored and the censoring indicators are missing at random, and establish the asymptotic normality of these estimators. As their applications, we derive the weighted local linear calibration estimators and imputation estimations of the conditional distribution function, the conditional density function and the conditional quantile function, and investigate the asymptotic normality of these estimators. Finally, the simulation studies are conducted to illustrate the finite sample performance of the estimators.

Keywords

Local polynomial estimation / asymptotic normality / non-parametric function / censoring indicator / missing at random

References

[1] Brunel E, Comte F, Guilloux A. Nonparametric estimation for survival data with censoring indicators missing at random. J Statist Plann Inference, 2013, 143 (10): 1653- 1671

[2] Dikta G. On semiparametric random censorship models. J Statist Plann Inference, 1998, 66 (2): 253- 279

[3] El Ghouch A, Van Keilegom I. Non-parametric regression with dependent censored data. Scand J Statist, 2008, 35 (2): 228- 247

[4] Fan J Q. Local linear regression smoothers and their minimax efficiencies. Ann Statist, 1993, 21 (1): 196- 216

[5] Fan J Q, Gijbels I. Censored regression: local linear approximations and their applications. J Amer Statist Assoc, 1994, 89 (426): 560- 570

[6] Fan J Q, Yao Q W, Tong H. Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems. Biometrika, 1996, 83 (1): 189- 206

[7] Guessoum Z, Ould-Saïd E. On nonparametric estimation of the regression function under random censorship model. Statist Decisions, 2008, 26 (3): 159- 177

[8] Guessoum Z, Ould-Saïd E. Central limit theorem for the kernel estimator of the regression function for censored time series. J Nonparametr Stat, 2012, 24 (2): 379- 397

[9] Li X Y, Wang Q H. The weighted least square based estimators with censoring indicators missing at random. J Statist Plann Inference, 2012, 142 (11): 2913- 2925

[10] Liang H Y, de Uña-Álvarez J. Asymptotic properties of conditional quantile estimator for censored dependent observations. Ann Inst Statist Math, 2011, 63 (2): 267- 289

[11] Little R J A, Rubin D B. Statistical Analysis with Missing Data, Second Edition, Wiley Series in Probability and Statistics, Hoboken, NJ: Wiley-Interscience, 2002

[12] McKeague I W, Subramanian S. Product-limit estimators and Cox regression with missing censoring information. Scand J Statist, 1998, 25 (4): 589- 601

[13] Nadaraya E A. On estimating regression. Theory Probab Appl, 1964, 9 (1): 141- 142

[14] Ould-Saïd E. A strong uniform convergence rate of kernel conditional quantile estimator under random censorship. Statist Probab Lett, 2006, 76 (6): 579- 586

[15] Shen Y, Liang H Y. Quantile regression for partially linear varying-coefficient model with censoring indicators missing at random. Comput Statist Data Anal, 2018, 117: 1- 18

[16] Silverman B W. Some aspects of the spline smoothing approach to nonparametric regression curve fitting, with discussion. J Roy Statist Soc Ser B, 1985, 47 (1): 1- 52

[17] Tang L J, Zhou Z G, Wu C C. Weighted composite quantile estimation and variable selection method for censored regression model. Statist Probab Lett, 2012, 82 (3): 653- 663

[18] Wang J L, Zheng M. Nonparametric regression estimation with missing censoring indicators. Chinese J Appl Probab Statist, 2014, 30 (5): 476- 490

[19] Wang Q H, Ng K W. Asymptotically efficient product-limit estimators with censoring indicators missing at random. Statist Sinica, 2008, 18 (2): 749- 768

[20] Yao M, Wang J F, Lin L. Double-kernel local linear estimator of conditional quantile under left-truncated and dependent data. Acta Math Sin (Chin Ser), 2018, 61 (6): 963- 980

[21] Yu K M, Jones M C. Local linear quantile regression. J Amer Statist Assoc, 1998, 93 (441): 228- 237

[22] Zhou L Z. A simple censored median regression estimator. Statist Sinica, 2016, 16 (3): 1043- 1058

[23] Zhou X, Sun L Q. Additive hazards regression with missing censoring information. Statist Sinica, 2003, 13 (4): 1237- 1257

RIGHTS & PERMISSIONS

Higher Education Press