Impact of dependent left truncation in semiparametric competing risks methods

A simulation study

Giorgos Bakoyannis, Giota Touloumi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this study, we investigated the robustness of the methods that account for independent left truncation when applied to competing risks settings with dependent left truncation. We specifically focused on the methods for the proportional cause-specific hazards model and the Fine–Gray model. Simulation experiments showed that these methods are not in general robust against dependent left truncation. The magnitude of the bias was analogous to the strength of the association between left truncation and failure times, the effect of the covariate on the competing cause of failure, and the baseline hazard of left truncation time.

Original languageEnglish (US)
Pages (from-to)2025-2042
Number of pages18
JournalCommunications in Statistics: Simulation and Computation
Volume46
Issue number3
DOIs
StatePublished - Mar 16 2017

Fingerprint

Left Truncation
Competing Risks
Hazards
Simulation Study
Dependent
Cause-specific Hazard
Hazard Models
Proportional Hazards
Failure Time
Hazard
Experiments
Simulation Experiment
Covariates
Baseline
Robustness

Keywords

  • Cause-specific hazards model
  • Competing risks
  • Fine–Gray model
  • Late entry
  • Left truncation

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation

Cite this

Impact of dependent left truncation in semiparametric competing risks methods : A simulation study. / Bakoyannis, Giorgos; Touloumi, Giota.

In: Communications in Statistics: Simulation and Computation, Vol. 46, No. 3, 16.03.2017, p. 2025-2042.

Research output: Contribution to journalArticle

@article{dfb9e13d2a504f878cf33677e27aa55c,
title = "Impact of dependent left truncation in semiparametric competing risks methods: A simulation study",
abstract = "In this study, we investigated the robustness of the methods that account for independent left truncation when applied to competing risks settings with dependent left truncation. We specifically focused on the methods for the proportional cause-specific hazards model and the Fine–Gray model. Simulation experiments showed that these methods are not in general robust against dependent left truncation. The magnitude of the bias was analogous to the strength of the association between left truncation and failure times, the effect of the covariate on the competing cause of failure, and the baseline hazard of left truncation time.",
keywords = "Cause-specific hazards model, Competing risks, Fine–Gray model, Late entry, Left truncation",
author = "Giorgos Bakoyannis and Giota Touloumi",
year = "2017",
month = "3",
day = "16",
doi = "10.1080/03610918.2015.1030415",
language = "English (US)",
volume = "46",
pages = "2025--2042",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Impact of dependent left truncation in semiparametric competing risks methods

T2 - A simulation study

AU - Bakoyannis, Giorgos

AU - Touloumi, Giota

PY - 2017/3/16

Y1 - 2017/3/16

N2 - In this study, we investigated the robustness of the methods that account for independent left truncation when applied to competing risks settings with dependent left truncation. We specifically focused on the methods for the proportional cause-specific hazards model and the Fine–Gray model. Simulation experiments showed that these methods are not in general robust against dependent left truncation. The magnitude of the bias was analogous to the strength of the association between left truncation and failure times, the effect of the covariate on the competing cause of failure, and the baseline hazard of left truncation time.

AB - In this study, we investigated the robustness of the methods that account for independent left truncation when applied to competing risks settings with dependent left truncation. We specifically focused on the methods for the proportional cause-specific hazards model and the Fine–Gray model. Simulation experiments showed that these methods are not in general robust against dependent left truncation. The magnitude of the bias was analogous to the strength of the association between left truncation and failure times, the effect of the covariate on the competing cause of failure, and the baseline hazard of left truncation time.

KW - Cause-specific hazards model

KW - Competing risks

KW - Fine–Gray model

KW - Late entry

KW - Left truncation

UR - http://www.scopus.com/inward/record.url?scp=84996549435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996549435&partnerID=8YFLogxK

U2 - 10.1080/03610918.2015.1030415

DO - 10.1080/03610918.2015.1030415

M3 - Article

VL - 46

SP - 2025

EP - 2042

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 3

ER -