Miscellanea. On nonidentifiability and noninformative censoring for current status data.

Research output: Contribution to journalArticle

Abstract

The event times and examination times that produce current status data are typically assumed to be independent. Here, an increasing sequence of nested models is considered for current status data, namely independence models, 'constant sum' models and models for which the conditional probability of the occurrence of the event prior to the examination time, given the examination time, is nondecreasing in the examination time. In the class of constant sum models, the distribution of the event time is identifiable and the examination times are noninformative. In the class of models with nondecreasing conditional probability, the distribution of the event time is nonidentifiable. Outside this class, the examination times cannot be ignored.
Original languageEnglish (US)
Pages (from-to)218-221
Number of pages4
JournalBiometrika
Volume87
Issue number1
DOIs
StatePublished - Mar 1 2000

Fingerprint

Current Status Data
Censoring
Conditional probability
probability distribution
Nested Models
Model
Monotonic increasing sequence

Keywords

  • SEQUENTIAL analysis
  • STOCHASTIC learning models
  • DISTRIBUTION (Probability theory)
  • ESTIMATION theory
  • STOCHASTIC processes
  • Constant sum model

Cite this

Miscellanea. On nonidentifiability and noninformative censoring for current status data. / Betensky, Rebecca A.

In: Biometrika, Vol. 87, No. 1, 01.03.2000, p. 218-221.

Research output: Contribution to journalArticle

@article{f07eb5de729c4c3f9331d894cc4ed215,
title = "Miscellanea. On nonidentifiability and noninformative censoring for current status data.",
abstract = "The event times and examination times that produce current status data are typically assumed to be independent. Here, an increasing sequence of nested models is considered for current status data, namely independence models, 'constant sum' models and models for which the conditional probability of the occurrence of the event prior to the examination time, given the examination time, is nondecreasing in the examination time. In the class of constant sum models, the distribution of the event time is identifiable and the examination times are noninformative. In the class of models with nondecreasing conditional probability, the distribution of the event time is nonidentifiable. Outside this class, the examination times cannot be ignored.",
keywords = "SEQUENTIAL analysis, STOCHASTIC learning models, DISTRIBUTION (Probability theory), ESTIMATION theory, STOCHASTIC processes, Constant sum model",
author = "Betensky, {Rebecca A.}",
year = "2000",
month = "3",
day = "1",
doi = "10.1093/biomet/87.1.218",
language = "English (US)",
volume = "87",
pages = "218--221",
journal = "Biometrika",
issn = "0006-3444",
publisher = "Oxford University Press",
number = "1",

}

TY - JOUR

T1 - Miscellanea. On nonidentifiability and noninformative censoring for current status data.

AU - Betensky, Rebecca A.

PY - 2000/3/1

Y1 - 2000/3/1

N2 - The event times and examination times that produce current status data are typically assumed to be independent. Here, an increasing sequence of nested models is considered for current status data, namely independence models, 'constant sum' models and models for which the conditional probability of the occurrence of the event prior to the examination time, given the examination time, is nondecreasing in the examination time. In the class of constant sum models, the distribution of the event time is identifiable and the examination times are noninformative. In the class of models with nondecreasing conditional probability, the distribution of the event time is nonidentifiable. Outside this class, the examination times cannot be ignored.

AB - The event times and examination times that produce current status data are typically assumed to be independent. Here, an increasing sequence of nested models is considered for current status data, namely independence models, 'constant sum' models and models for which the conditional probability of the occurrence of the event prior to the examination time, given the examination time, is nondecreasing in the examination time. In the class of constant sum models, the distribution of the event time is identifiable and the examination times are noninformative. In the class of models with nondecreasing conditional probability, the distribution of the event time is nonidentifiable. Outside this class, the examination times cannot be ignored.

KW - SEQUENTIAL analysis

KW - STOCHASTIC learning models

KW - DISTRIBUTION (Probability theory)

KW - ESTIMATION theory

KW - STOCHASTIC processes

KW - Constant sum model

U2 - 10.1093/biomet/87.1.218

DO - 10.1093/biomet/87.1.218

M3 - Article

VL - 87

SP - 218

EP - 221

JO - Biometrika

JF - Biometrika

SN - 0006-3444

IS - 1

ER -