Testing quasi-independence of failure and truncation times via conditional kendall's tau

Emily C. Martin, Rebecca Betensky

Research output: Contribution to journalArticle

Abstract

Truncated survival data arise when the failure time is observed only if it falls within a subject-specific truncating set. Most analysis methods rely on the key assumption of quasi-independence, that is, factorization of the joint density of failure and truncation times into a product proportional to the individual densities in the observable region. Unlike independence of failure time and censoring time, quasi-independence can be tested. Tests of quasi-independence are available for one-sided truncation and for truncation that depends on a measured covariate, but not for more complex truncation schemes. Here tests of quasi-independenee based on a multivariate conditional Kendall's tau are proposed for doubly truncated data, bivariate left-truncated data, and other forms of truncated survival data that arise when initiating or terminating event times are interval-censored. Asymptotic properties under the null are derived. The tests are illustrated using several real datasets and evaluated via simulation.

Original languageEnglish (US)
Pages (from-to)484-492
Number of pages9
JournalJournal of the American Statistical Association
Volume100
Issue number470
DOIs
StatePublished - Jun 1 2005

Fingerprint

Quasi-independence
Kendall's tau
Truncated Data
Truncation
Testing
Survival Data
Failure Time
Censoring
Asymptotic Properties
Null
Covariates
Factorization
Directly proportional
Interval
Simulation

Keywords

  • Dependence
  • Truncated data
  • U-statistic

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

Testing quasi-independence of failure and truncation times via conditional kendall's tau. / Martin, Emily C.; Betensky, Rebecca.

In: Journal of the American Statistical Association, Vol. 100, No. 470, 01.06.2005, p. 484-492.

Research output: Contribution to journalArticle

@article{432db56fcb194e528548157fae7b6a07,
title = "Testing quasi-independence of failure and truncation times via conditional kendall's tau",
abstract = "Truncated survival data arise when the failure time is observed only if it falls within a subject-specific truncating set. Most analysis methods rely on the key assumption of quasi-independence, that is, factorization of the joint density of failure and truncation times into a product proportional to the individual densities in the observable region. Unlike independence of failure time and censoring time, quasi-independence can be tested. Tests of quasi-independence are available for one-sided truncation and for truncation that depends on a measured covariate, but not for more complex truncation schemes. Here tests of quasi-independenee based on a multivariate conditional Kendall's tau are proposed for doubly truncated data, bivariate left-truncated data, and other forms of truncated survival data that arise when initiating or terminating event times are interval-censored. Asymptotic properties under the null are derived. The tests are illustrated using several real datasets and evaluated via simulation.",
keywords = "Dependence, Truncated data, U-statistic",
author = "Martin, {Emily C.} and Rebecca Betensky",
year = "2005",
month = "6",
day = "1",
doi = "10.1198/016214504000001538",
language = "English (US)",
volume = "100",
pages = "484--492",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "470",

}

TY - JOUR

T1 - Testing quasi-independence of failure and truncation times via conditional kendall's tau

AU - Martin, Emily C.

AU - Betensky, Rebecca

PY - 2005/6/1

Y1 - 2005/6/1

N2 - Truncated survival data arise when the failure time is observed only if it falls within a subject-specific truncating set. Most analysis methods rely on the key assumption of quasi-independence, that is, factorization of the joint density of failure and truncation times into a product proportional to the individual densities in the observable region. Unlike independence of failure time and censoring time, quasi-independence can be tested. Tests of quasi-independence are available for one-sided truncation and for truncation that depends on a measured covariate, but not for more complex truncation schemes. Here tests of quasi-independenee based on a multivariate conditional Kendall's tau are proposed for doubly truncated data, bivariate left-truncated data, and other forms of truncated survival data that arise when initiating or terminating event times are interval-censored. Asymptotic properties under the null are derived. The tests are illustrated using several real datasets and evaluated via simulation.

AB - Truncated survival data arise when the failure time is observed only if it falls within a subject-specific truncating set. Most analysis methods rely on the key assumption of quasi-independence, that is, factorization of the joint density of failure and truncation times into a product proportional to the individual densities in the observable region. Unlike independence of failure time and censoring time, quasi-independence can be tested. Tests of quasi-independence are available for one-sided truncation and for truncation that depends on a measured covariate, but not for more complex truncation schemes. Here tests of quasi-independenee based on a multivariate conditional Kendall's tau are proposed for doubly truncated data, bivariate left-truncated data, and other forms of truncated survival data that arise when initiating or terminating event times are interval-censored. Asymptotic properties under the null are derived. The tests are illustrated using several real datasets and evaluated via simulation.

KW - Dependence

KW - Truncated data

KW - U-statistic

UR - http://www.scopus.com/inward/record.url?scp=20444468546&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20444468546&partnerID=8YFLogxK

U2 - 10.1198/016214504000001538

DO - 10.1198/016214504000001538

M3 - Article

AN - SCOPUS:20444468546

VL - 100

SP - 484

EP - 492

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 470

ER -