Local likelihood analysis of the latency distribution with interval censored intermediate events

Judith D. Bebchuk, Rebecca Betensky

Research output: Contribution to journalArticle

Abstract

The distribution of time between an intermediate event and a terminal event is frequently of interest both in studying the behaviour of populations and in predicting outcomes for individuals. Current methods for estimating this latency distribution have either imposed assumptions on the hazard for the terminal event following the occurrence of the intermediate event or on the parametric form of the hazards. Here, local likelihood estimation is applied to the underlying hazard functions of a three-state process in which the time of the intermediate event may be interval censored and the time of the terminal event is either observed or right censored. Smooth non-parametric estimates of the latency distribution, along with bootstrap confidence intervals, are calculated, and tests for the comparison of two latency distributions are presented. The method is applied to two studies: a cohort of haemophiliacs who were infected with HIV by contaminated blood factor and followed for AIDS onset, and an AIDS clinical trial in which the intermediate event is the time to 50 per cent drop in CD4 count and the terminal event is AIDS or death. Simulations are presented to assess the performance of the estimation procedure.

Original languageEnglish (US)
Pages (from-to)3475-3491
Number of pages17
JournalStatistics in Medicine
Volume21
Issue number22
DOIs
StatePublished - Nov 30 2002

Fingerprint

Local Likelihood
Latency
Acquired Immunodeficiency Syndrome
Interval
CD4 Lymphocyte Count
Hazard
Cohort Studies
Clinical Trials
HIV
Confidence Intervals
Bootstrap Confidence Intervals
Hazard Function
Population
Blood
Count

Keywords

  • Hazard estimation
  • Smoothing
  • Three-state model

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Local likelihood analysis of the latency distribution with interval censored intermediate events. / Bebchuk, Judith D.; Betensky, Rebecca.

In: Statistics in Medicine, Vol. 21, No. 22, 30.11.2002, p. 3475-3491.

Research output: Contribution to journalArticle

@article{e2dd407681234d5baaaea5f6d0b53c90,
title = "Local likelihood analysis of the latency distribution with interval censored intermediate events",
abstract = "The distribution of time between an intermediate event and a terminal event is frequently of interest both in studying the behaviour of populations and in predicting outcomes for individuals. Current methods for estimating this latency distribution have either imposed assumptions on the hazard for the terminal event following the occurrence of the intermediate event or on the parametric form of the hazards. Here, local likelihood estimation is applied to the underlying hazard functions of a three-state process in which the time of the intermediate event may be interval censored and the time of the terminal event is either observed or right censored. Smooth non-parametric estimates of the latency distribution, along with bootstrap confidence intervals, are calculated, and tests for the comparison of two latency distributions are presented. The method is applied to two studies: a cohort of haemophiliacs who were infected with HIV by contaminated blood factor and followed for AIDS onset, and an AIDS clinical trial in which the intermediate event is the time to 50 per cent drop in CD4 count and the terminal event is AIDS or death. Simulations are presented to assess the performance of the estimation procedure.",
keywords = "Hazard estimation, Smoothing, Three-state model",
author = "Bebchuk, {Judith D.} and Rebecca Betensky",
year = "2002",
month = "11",
day = "30",
doi = "10.1002/sim.1275",
language = "English (US)",
volume = "21",
pages = "3475--3491",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "22",

}

TY - JOUR

T1 - Local likelihood analysis of the latency distribution with interval censored intermediate events

AU - Bebchuk, Judith D.

AU - Betensky, Rebecca

PY - 2002/11/30

Y1 - 2002/11/30

N2 - The distribution of time between an intermediate event and a terminal event is frequently of interest both in studying the behaviour of populations and in predicting outcomes for individuals. Current methods for estimating this latency distribution have either imposed assumptions on the hazard for the terminal event following the occurrence of the intermediate event or on the parametric form of the hazards. Here, local likelihood estimation is applied to the underlying hazard functions of a three-state process in which the time of the intermediate event may be interval censored and the time of the terminal event is either observed or right censored. Smooth non-parametric estimates of the latency distribution, along with bootstrap confidence intervals, are calculated, and tests for the comparison of two latency distributions are presented. The method is applied to two studies: a cohort of haemophiliacs who were infected with HIV by contaminated blood factor and followed for AIDS onset, and an AIDS clinical trial in which the intermediate event is the time to 50 per cent drop in CD4 count and the terminal event is AIDS or death. Simulations are presented to assess the performance of the estimation procedure.

AB - The distribution of time between an intermediate event and a terminal event is frequently of interest both in studying the behaviour of populations and in predicting outcomes for individuals. Current methods for estimating this latency distribution have either imposed assumptions on the hazard for the terminal event following the occurrence of the intermediate event or on the parametric form of the hazards. Here, local likelihood estimation is applied to the underlying hazard functions of a three-state process in which the time of the intermediate event may be interval censored and the time of the terminal event is either observed or right censored. Smooth non-parametric estimates of the latency distribution, along with bootstrap confidence intervals, are calculated, and tests for the comparison of two latency distributions are presented. The method is applied to two studies: a cohort of haemophiliacs who were infected with HIV by contaminated blood factor and followed for AIDS onset, and an AIDS clinical trial in which the intermediate event is the time to 50 per cent drop in CD4 count and the terminal event is AIDS or death. Simulations are presented to assess the performance of the estimation procedure.

KW - Hazard estimation

KW - Smoothing

KW - Three-state model

UR - http://www.scopus.com/inward/record.url?scp=0037202581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037202581&partnerID=8YFLogxK

U2 - 10.1002/sim.1275

DO - 10.1002/sim.1275

M3 - Article

VL - 21

SP - 3475

EP - 3491

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 22

ER -