Median regression from twice censored data

Sundarraman Subramanian

doi:10.1016/j.spl.2020.108955

Median regression from twice censored data

Sundarraman Subramanian

Mathematical Sciences

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

An adjusted least absolute deviation estimating function, founded on the inverse (probability of) censoring weighted approach, is proposed. Covariate-free left and right censoring is assumed. When left censoring is absent, the proposed estimating function reduces to its right-censored counterpart. Consistency and asymptotic normality of the estimator of the regression parameter are derived. Finite sample performance is investigated via simulations. Application of the proposed method is illustrated using some synthetic data sets.

Original language	English (US)
Article number	108955
Journal	Statistics and Probability Letters
Volume	168
DOIs	https://doi.org/10.1016/j.spl.2020.108955
State	Published - Jan 2021

All Science Journal Classification (ASJC) codes

Statistics and Probability
Statistics, Probability and Uncertainty

Keywords

Curse of dimensionality
Empirical likelihood
Local linearity
Measure preserving transformation
Minimum dispersion statistic
Subset inference

Access to Document

10.1016/j.spl.2020.108955

Cite this

@article{d53f1dd7390847de8c2d631ff089f16e,

title = "Median regression from twice censored data",

abstract = "An adjusted least absolute deviation estimating function, founded on the inverse (probability of) censoring weighted approach, is proposed. Covariate-free left and right censoring is assumed. When left censoring is absent, the proposed estimating function reduces to its right-censored counterpart. Consistency and asymptotic normality of the estimator of the regression parameter are derived. Finite sample performance is investigated via simulations. Application of the proposed method is illustrated using some synthetic data sets.",

keywords = "Curse of dimensionality, Empirical likelihood, Local linearity, Measure preserving transformation, Minimum dispersion statistic, Subset inference",

author = "Sundarraman Subramanian",

note = "Publisher Copyright: {\textcopyright} 2020 Elsevier B.V.",

year = "2021",

month = jan,

doi = "10.1016/j.spl.2020.108955",

language = "English (US)",

volume = "168",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Median regression from twice censored data

AU - Subramanian, Sundarraman

PY - 2021/1

Y1 - 2021/1

N2 - An adjusted least absolute deviation estimating function, founded on the inverse (probability of) censoring weighted approach, is proposed. Covariate-free left and right censoring is assumed. When left censoring is absent, the proposed estimating function reduces to its right-censored counterpart. Consistency and asymptotic normality of the estimator of the regression parameter are derived. Finite sample performance is investigated via simulations. Application of the proposed method is illustrated using some synthetic data sets.

AB - An adjusted least absolute deviation estimating function, founded on the inverse (probability of) censoring weighted approach, is proposed. Covariate-free left and right censoring is assumed. When left censoring is absent, the proposed estimating function reduces to its right-censored counterpart. Consistency and asymptotic normality of the estimator of the regression parameter are derived. Finite sample performance is investigated via simulations. Application of the proposed method is illustrated using some synthetic data sets.

KW - Curse of dimensionality

KW - Empirical likelihood

KW - Local linearity

KW - Measure preserving transformation

KW - Minimum dispersion statistic

KW - Subset inference

UR - http://www.scopus.com/inward/record.url?scp=85092054970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85092054970&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2020.108955

DO - 10.1016/j.spl.2020.108955

M3 - Article

AN - SCOPUS:85092054970

SN - 0167-7152

VL - 168

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

M1 - 108955

ER -

Median regression from twice censored data

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this