Randomly censored partially linear single-index models

Xuewen Lu, Tsung-Lin Cheng

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

This paper proposes a method for estimation of a class of partially linear single-index models with randomly censored samples. The method provides a flexible way for modelling the association between a response and a set of predictor variables when the response variable is randomly censored. It presents a technique for "dimension reduction" in semiparametric censored regression models and generalizes the existing accelerated failure-time models for survival analysis. The estimation procedure involves three stages: first, transform the censored data into synthetic data or pseudo-responses unbiasedly; second, obtain quasi-likelihood estimates of the regression coefficients in both linear and single-index components by an iteratively algorithm; finally, estimate the unknown nonparametric regression function using techniques for univariate censored nonparametric regression. The estimators for the regression coefficients are shown to be jointly root-n consistent and asymptotically normal. In addition, the estimator for the unknown regression function is a local linear kernel regression estimator and can be estimated with the same efficiency as all the parameters are known. Monte Carlo simulations are conducted to illustrate the proposed methodology.

Original languageEnglish
Pages (from-to)1895-1922
Number of pages28
JournalJournal of Multivariate Analysis
Volume98
Issue number10
DOIs
Publication statusPublished - 2007 Nov 1

Fingerprint

Single-index Model
Censored Regression
Linear Model
Nonparametric Regression
Regression Function
Regression Coefficient
Accelerated Failure Time Model
Semiparametric Regression
Estimator
Unknown
Kernel Regression
Censored Samples
Quasi-likelihood
Regression Estimator
Kernel Estimator
Survival Analysis
Censored Data
Dimension Reduction
Synthetic Data
Linear regression

All Science Journal Classification (ASJC) codes

  • Statistics, Probability and Uncertainty
  • Numerical Analysis
  • Statistics and Probability

Cite this

@article{696ec429bcc3449eabbf4d45e8f4beb8,
title = "Randomly censored partially linear single-index models",
abstract = "This paper proposes a method for estimation of a class of partially linear single-index models with randomly censored samples. The method provides a flexible way for modelling the association between a response and a set of predictor variables when the response variable is randomly censored. It presents a technique for {"}dimension reduction{"} in semiparametric censored regression models and generalizes the existing accelerated failure-time models for survival analysis. The estimation procedure involves three stages: first, transform the censored data into synthetic data or pseudo-responses unbiasedly; second, obtain quasi-likelihood estimates of the regression coefficients in both linear and single-index components by an iteratively algorithm; finally, estimate the unknown nonparametric regression function using techniques for univariate censored nonparametric regression. The estimators for the regression coefficients are shown to be jointly root-n consistent and asymptotically normal. In addition, the estimator for the unknown regression function is a local linear kernel regression estimator and can be estimated with the same efficiency as all the parameters are known. Monte Carlo simulations are conducted to illustrate the proposed methodology.",
author = "Xuewen Lu and Tsung-Lin Cheng",
year = "2007",
month = "11",
day = "1",
doi = "10.1016/j.jmva.2006.11.008",
language = "English",
volume = "98",
pages = "1895--1922",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "10",

}

Randomly censored partially linear single-index models. / Lu, Xuewen; Cheng, Tsung-Lin.

In: Journal of Multivariate Analysis, Vol. 98, No. 10, 01.11.2007, p. 1895-1922.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Randomly censored partially linear single-index models

AU - Lu, Xuewen

AU - Cheng, Tsung-Lin

PY - 2007/11/1

Y1 - 2007/11/1

N2 - This paper proposes a method for estimation of a class of partially linear single-index models with randomly censored samples. The method provides a flexible way for modelling the association between a response and a set of predictor variables when the response variable is randomly censored. It presents a technique for "dimension reduction" in semiparametric censored regression models and generalizes the existing accelerated failure-time models for survival analysis. The estimation procedure involves three stages: first, transform the censored data into synthetic data or pseudo-responses unbiasedly; second, obtain quasi-likelihood estimates of the regression coefficients in both linear and single-index components by an iteratively algorithm; finally, estimate the unknown nonparametric regression function using techniques for univariate censored nonparametric regression. The estimators for the regression coefficients are shown to be jointly root-n consistent and asymptotically normal. In addition, the estimator for the unknown regression function is a local linear kernel regression estimator and can be estimated with the same efficiency as all the parameters are known. Monte Carlo simulations are conducted to illustrate the proposed methodology.

AB - This paper proposes a method for estimation of a class of partially linear single-index models with randomly censored samples. The method provides a flexible way for modelling the association between a response and a set of predictor variables when the response variable is randomly censored. It presents a technique for "dimension reduction" in semiparametric censored regression models and generalizes the existing accelerated failure-time models for survival analysis. The estimation procedure involves three stages: first, transform the censored data into synthetic data or pseudo-responses unbiasedly; second, obtain quasi-likelihood estimates of the regression coefficients in both linear and single-index components by an iteratively algorithm; finally, estimate the unknown nonparametric regression function using techniques for univariate censored nonparametric regression. The estimators for the regression coefficients are shown to be jointly root-n consistent and asymptotically normal. In addition, the estimator for the unknown regression function is a local linear kernel regression estimator and can be estimated with the same efficiency as all the parameters are known. Monte Carlo simulations are conducted to illustrate the proposed methodology.

UR - http://www.scopus.com/inward/record.url?scp=35348934326&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35348934326&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2006.11.008

DO - 10.1016/j.jmva.2006.11.008

M3 - Article

VL - 98

SP - 1895

EP - 1922

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 10

ER -