PERFORMANCE OF LIKELIHOOD-BASED INTERVAL ESTIMATES FOR TWO-PARAMETER EXPONENTIAL SAMPLES SUBJECT TO TYPE I CENSORING.

Walter W Piegorsch, Research Triangle Park Natl Inst of Environmental Health Sciences

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Inferences on the parameters in a two-parameter exponential lifetime model when the data are Type I censored are limited to asymptotic approximations or to conditional constructions around the observed number of lifetimes. The asymptotic methods are simple to implement when constructing confidence regions on the scale and guarantee time parameters of the model. Their small sample properties have not been previously explored, however. This study provides Monte Carlo results to evaluate these properties. For univariate inference on the scale parameter, convergence of the coverage probabilities to nominal levels is slow until the sample size reaches 25. For the guarantee time parameter, two asymptotically equivalent procedures behave similarly, an F-distribution-based method performing slightly better for smaller sample sizes.

Original languageEnglish (US)
Pages (from-to)41-49
Number of pages9
JournalTechnometrics
Volume29
Issue number1
StatePublished - Feb 1987
Externally publishedYes

Fingerprint

Type I Censoring
Two Parameters
Lifetime
Likelihood
F distribution
Interval
Asymptotically equivalent
Confidence Region
Coverage Probability
Small Sample Size
Asymptotic Approximation
Asymptotic Methods
Scale Parameter
Monte Carlo Study
Small Sample
Estimate
Univariate
Categorical or nominal
Sample Size
Evaluate

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

PERFORMANCE OF LIKELIHOOD-BASED INTERVAL ESTIMATES FOR TWO-PARAMETER EXPONENTIAL SAMPLES SUBJECT TO TYPE I CENSORING. / Piegorsch, Walter W; Natl Inst of Environmental Health Sciences, Research Triangle Park.

In: Technometrics, Vol. 29, No. 1, 02.1987, p. 41-49.

Research output: Contribution to journalArticle

Piegorsch, Walter W ; Natl Inst of Environmental Health Sciences, Research Triangle Park. / PERFORMANCE OF LIKELIHOOD-BASED INTERVAL ESTIMATES FOR TWO-PARAMETER EXPONENTIAL SAMPLES SUBJECT TO TYPE I CENSORING. In: Technometrics. 1987 ; Vol. 29, No. 1. pp. 41-49.
@article{8cb38562f36b40a2896938b761ea5d91,
title = "PERFORMANCE OF LIKELIHOOD-BASED INTERVAL ESTIMATES FOR TWO-PARAMETER EXPONENTIAL SAMPLES SUBJECT TO TYPE I CENSORING.",
abstract = "Inferences on the parameters in a two-parameter exponential lifetime model when the data are Type I censored are limited to asymptotic approximations or to conditional constructions around the observed number of lifetimes. The asymptotic methods are simple to implement when constructing confidence regions on the scale and guarantee time parameters of the model. Their small sample properties have not been previously explored, however. This study provides Monte Carlo results to evaluate these properties. For univariate inference on the scale parameter, convergence of the coverage probabilities to nominal levels is slow until the sample size reaches 25. For the guarantee time parameter, two asymptotically equivalent procedures behave similarly, an F-distribution-based method performing slightly better for smaller sample sizes.",
author = "Piegorsch, {Walter W} and {Natl Inst of Environmental Health Sciences}, {Research Triangle Park}",
year = "1987",
month = "2",
language = "English (US)",
volume = "29",
pages = "41--49",
journal = "Technometrics",
issn = "0040-1706",
publisher = "American Statistical Association",
number = "1",

}

TY - JOUR

T1 - PERFORMANCE OF LIKELIHOOD-BASED INTERVAL ESTIMATES FOR TWO-PARAMETER EXPONENTIAL SAMPLES SUBJECT TO TYPE I CENSORING.

AU - Piegorsch, Walter W

AU - Natl Inst of Environmental Health Sciences, Research Triangle Park

PY - 1987/2

Y1 - 1987/2

N2 - Inferences on the parameters in a two-parameter exponential lifetime model when the data are Type I censored are limited to asymptotic approximations or to conditional constructions around the observed number of lifetimes. The asymptotic methods are simple to implement when constructing confidence regions on the scale and guarantee time parameters of the model. Their small sample properties have not been previously explored, however. This study provides Monte Carlo results to evaluate these properties. For univariate inference on the scale parameter, convergence of the coverage probabilities to nominal levels is slow until the sample size reaches 25. For the guarantee time parameter, two asymptotically equivalent procedures behave similarly, an F-distribution-based method performing slightly better for smaller sample sizes.

AB - Inferences on the parameters in a two-parameter exponential lifetime model when the data are Type I censored are limited to asymptotic approximations or to conditional constructions around the observed number of lifetimes. The asymptotic methods are simple to implement when constructing confidence regions on the scale and guarantee time parameters of the model. Their small sample properties have not been previously explored, however. This study provides Monte Carlo results to evaluate these properties. For univariate inference on the scale parameter, convergence of the coverage probabilities to nominal levels is slow until the sample size reaches 25. For the guarantee time parameter, two asymptotically equivalent procedures behave similarly, an F-distribution-based method performing slightly better for smaller sample sizes.

UR - http://www.scopus.com/inward/record.url?scp=0023288392&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023288392&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0023288392

VL - 29

SP - 41

EP - 49

JO - Technometrics

JF - Technometrics

SN - 0040-1706

IS - 1

ER -