On the assumption of independent right censoring

Morten Overgaard; Stefan Nygaard Hansen

doi:10.1111/sjos.12487

On the assumption of independent right censoring

Morten Overgaard^*, Stefan Nygaard Hansen

^*Corresponding author af dette arbejde

Institut for Folkesundhed - Biostatistik

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

2 Citationer (Scopus)

Abstract

Various assumptions on a right-censoring mechanism to ensure consistency of the Kaplan–Meier and Aalen–Johansen estimators in a competing risks setting are studied. Specifically, eight different assumptions are seen to fall in two categories: a weaker identifiability assumption, which is the weakest possible assumption in a precise sense, and a stronger representativity assumption which ensures the existence of an independent censoring time. When a given censoring time is considered, similar assumptions can be made on the censoring time. This allows for a characterization of so-called pointwise independence as well as full independence of censoring time and event time and type. Examples illustrate how the various assumptions differ.

Originalsprog	Engelsk
Tidsskrift	Scandinavian Journal of Statistics
Vol/bind	48
Nummer	4
Sider (fra-til)	1234-1255
Antal sider	22
ISSN	0303-6898
DOI	https://doi.org/10.1111/sjos.12487
Status	Udgivet - dec. 2021

Adgang til dokumentet

10.1111/sjos.12487

https://arxiv.org/pdf/1905.02508

Andre filer og links

Link to publication in Scopus

Citationsformater

@article{d44944502da94c0cae75e43d2aab001a,

title = "On the assumption of independent right censoring",

abstract = "Various assumptions on a right-censoring mechanism to ensure consistency of the Kaplan–Meier and Aalen–Johansen estimators in a competing risks setting are studied. Specifically, eight different assumptions are seen to fall in two categories: a weaker identifiability assumption, which is the weakest possible assumption in a precise sense, and a stronger representativity assumption which ensures the existence of an independent censoring time. When a given censoring time is considered, similar assumptions can be made on the censoring time. This allows for a characterization of so-called pointwise independence as well as full independence of censoring time and event time and type. Examples illustrate how the various assumptions differ.",

keywords = "censoring, competing risks, consistency, identifiability, product integral, representativity",

author = "Morten Overgaard and Hansen, {Stefan Nygaard}",

year = "2021",

month = dec,

doi = "10.1111/sjos.12487",

language = "English",

volume = "48",

pages = "1234--1255",

journal = "Scandinavian Journal of Statistics",

issn = "0303-6898",

publisher = "Wiley-Blackwell Publishing Ltd",

number = "4",

}

TY - JOUR

T1 - On the assumption of independent right censoring

AU - Overgaard, Morten

AU - Hansen, Stefan Nygaard

PY - 2021/12

Y1 - 2021/12

N2 - Various assumptions on a right-censoring mechanism to ensure consistency of the Kaplan–Meier and Aalen–Johansen estimators in a competing risks setting are studied. Specifically, eight different assumptions are seen to fall in two categories: a weaker identifiability assumption, which is the weakest possible assumption in a precise sense, and a stronger representativity assumption which ensures the existence of an independent censoring time. When a given censoring time is considered, similar assumptions can be made on the censoring time. This allows for a characterization of so-called pointwise independence as well as full independence of censoring time and event time and type. Examples illustrate how the various assumptions differ.

AB - Various assumptions on a right-censoring mechanism to ensure consistency of the Kaplan–Meier and Aalen–Johansen estimators in a competing risks setting are studied. Specifically, eight different assumptions are seen to fall in two categories: a weaker identifiability assumption, which is the weakest possible assumption in a precise sense, and a stronger representativity assumption which ensures the existence of an independent censoring time. When a given censoring time is considered, similar assumptions can be made on the censoring time. This allows for a characterization of so-called pointwise independence as well as full independence of censoring time and event time and type. Examples illustrate how the various assumptions differ.

KW - censoring

KW - competing risks

KW - consistency

KW - identifiability

KW - product integral

KW - representativity

UR - http://www.scopus.com/inward/record.url?scp=85091605226&partnerID=8YFLogxK

U2 - 10.1111/sjos.12487

DO - 10.1111/sjos.12487

M3 - Journal article

SN - 0303-6898

VL - 48

SP - 1234

EP - 1255

JO - Scandinavian Journal of Statistics

JF - Scandinavian Journal of Statistics

IS - 4

ER -

On the assumption of independent right censoring

Abstract

Adgang til dokumentet

Andre filer og links

Fingeraftryk

Citationsformater