Bayesian Nonparametric Nonproportional Hazards Survival Modeling

Maria De Iorio, Wesley O. Johnson, Peter Müller, Gary Rosner

Research output: Contribution to journalArticle

Abstract

We develop a dependent Dirichlet process model for survival analysis data. A major feature of the proposed approach is that there is no necessity for resulting survival curve estimates to satisfy the ubiquitous proportional hazards assumption. An illustration based on a cancer clinical trial is given, where survival probabilities for times early in the study are estimated to be lower for those on a high-dose treatment regimen than for those on the low dose treatment, while the reverse is true for later times, possibly due to the toxic effect of the high dose for those who are not as healthy at the beginning of the study.

Original languageEnglish (US)
Pages (from-to)762-771
Number of pages10
JournalBiometrics
Volume65
Issue number3
DOIs
StatePublished - Sep 2009
Externally publishedYes

Fingerprint

Non-proportional Hazards
Bayesian Nonparametrics
Poisons
Dose
Hazards
Survival Analysis
dosage
Modeling
Proportional Hazards
Dirichlet Process
Survival Probability
Clinical Trials
Process Model
Reverse
clinical trials
data analysis
Cancer
Neoplasms
Curve
neoplasms

Keywords

  • Censoring
  • Dependent Dirichlet process
  • Markov chain Monte Carlo

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Medicine(all)

Cite this

Bayesian Nonparametric Nonproportional Hazards Survival Modeling. / De Iorio, Maria; Johnson, Wesley O.; Müller, Peter; Rosner, Gary.

In: Biometrics, Vol. 65, No. 3, 09.2009, p. 762-771.

Research output: Contribution to journalArticle

De Iorio, Maria ; Johnson, Wesley O. ; Müller, Peter ; Rosner, Gary. / Bayesian Nonparametric Nonproportional Hazards Survival Modeling. In: Biometrics. 2009 ; Vol. 65, No. 3. pp. 762-771.
@article{7759a02d1f2145fd94ef5a024705271d,
title = "Bayesian Nonparametric Nonproportional Hazards Survival Modeling",
abstract = "We develop a dependent Dirichlet process model for survival analysis data. A major feature of the proposed approach is that there is no necessity for resulting survival curve estimates to satisfy the ubiquitous proportional hazards assumption. An illustration based on a cancer clinical trial is given, where survival probabilities for times early in the study are estimated to be lower for those on a high-dose treatment regimen than for those on the low dose treatment, while the reverse is true for later times, possibly due to the toxic effect of the high dose for those who are not as healthy at the beginning of the study.",
keywords = "Censoring, Dependent Dirichlet process, Markov chain Monte Carlo",
author = "{De Iorio}, Maria and Johnson, {Wesley O.} and Peter M{\"u}ller and Gary Rosner",
year = "2009",
month = "9",
doi = "10.1111/j.1541-0420.2008.01166.x",
language = "English (US)",
volume = "65",
pages = "762--771",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Bayesian Nonparametric Nonproportional Hazards Survival Modeling

AU - De Iorio, Maria

AU - Johnson, Wesley O.

AU - Müller, Peter

AU - Rosner, Gary

PY - 2009/9

Y1 - 2009/9

N2 - We develop a dependent Dirichlet process model for survival analysis data. A major feature of the proposed approach is that there is no necessity for resulting survival curve estimates to satisfy the ubiquitous proportional hazards assumption. An illustration based on a cancer clinical trial is given, where survival probabilities for times early in the study are estimated to be lower for those on a high-dose treatment regimen than for those on the low dose treatment, while the reverse is true for later times, possibly due to the toxic effect of the high dose for those who are not as healthy at the beginning of the study.

AB - We develop a dependent Dirichlet process model for survival analysis data. A major feature of the proposed approach is that there is no necessity for resulting survival curve estimates to satisfy the ubiquitous proportional hazards assumption. An illustration based on a cancer clinical trial is given, where survival probabilities for times early in the study are estimated to be lower for those on a high-dose treatment regimen than for those on the low dose treatment, while the reverse is true for later times, possibly due to the toxic effect of the high dose for those who are not as healthy at the beginning of the study.

KW - Censoring

KW - Dependent Dirichlet process

KW - Markov chain Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=70349246865&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349246865&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2008.01166.x

DO - 10.1111/j.1541-0420.2008.01166.x

M3 - Article

VL - 65

SP - 762

EP - 771

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -