Confidence intervals for the log-normal mean

Xiao Hua Zhou, Sujuan Gao

Research output: Contribution to journalArticle

124 Citations (Scopus)

Abstract

In this paper we conduct a simulation study to evaluate coverage error, interval width and relative bias of four main methods for the construction of confidence intervals of log-normal means: the naive method; Cox's method; a conservative method; and a parametric bootstrap method. The simulation study finds that the naive method is inappropriate, that Cox's method has the smallest coverage error for moderate and large sample sizes, and that the bootstrap method has the smallest coverage error for small sample sizes. In addition, Cox's method produces the smallest interval width among the three appropriate methods. We also apply the four methods to a real data set to contrast the differences.

Original languageEnglish
Pages (from-to)783-790
Number of pages8
JournalStatistics in Medicine
Volume16
Issue number7
DOIs
StatePublished - Apr 15 1997

Fingerprint

Confidence interval
Confidence Intervals
Coverage
Bootstrap Method
Sample Size
Simulation Study
Parametric Bootstrap
Interval
Small Sample Size
Evaluate

ASJC Scopus subject areas

  • Epidemiology

Cite this

Confidence intervals for the log-normal mean. / Zhou, Xiao Hua; Gao, Sujuan.

In: Statistics in Medicine, Vol. 16, No. 7, 15.04.1997, p. 783-790.

Research output: Contribution to journalArticle

Zhou, Xiao Hua ; Gao, Sujuan. / Confidence intervals for the log-normal mean. In: Statistics in Medicine. 1997 ; Vol. 16, No. 7. pp. 783-790.
@article{d0024da6284e4a61ab7f902bcaccd48e,
title = "Confidence intervals for the log-normal mean",
abstract = "In this paper we conduct a simulation study to evaluate coverage error, interval width and relative bias of four main methods for the construction of confidence intervals of log-normal means: the naive method; Cox's method; a conservative method; and a parametric bootstrap method. The simulation study finds that the naive method is inappropriate, that Cox's method has the smallest coverage error for moderate and large sample sizes, and that the bootstrap method has the smallest coverage error for small sample sizes. In addition, Cox's method produces the smallest interval width among the three appropriate methods. We also apply the four methods to a real data set to contrast the differences.",
author = "Zhou, {Xiao Hua} and Sujuan Gao",
year = "1997",
month = "4",
day = "15",
doi = "10.1002/(SICI)1097-0258(19970415)16:7<783::AID-SIM488>3.0.CO;2-2",
language = "English",
volume = "16",
pages = "783--790",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "7",

}

TY - JOUR

T1 - Confidence intervals for the log-normal mean

AU - Zhou, Xiao Hua

AU - Gao, Sujuan

PY - 1997/4/15

Y1 - 1997/4/15

N2 - In this paper we conduct a simulation study to evaluate coverage error, interval width and relative bias of four main methods for the construction of confidence intervals of log-normal means: the naive method; Cox's method; a conservative method; and a parametric bootstrap method. The simulation study finds that the naive method is inappropriate, that Cox's method has the smallest coverage error for moderate and large sample sizes, and that the bootstrap method has the smallest coverage error for small sample sizes. In addition, Cox's method produces the smallest interval width among the three appropriate methods. We also apply the four methods to a real data set to contrast the differences.

AB - In this paper we conduct a simulation study to evaluate coverage error, interval width and relative bias of four main methods for the construction of confidence intervals of log-normal means: the naive method; Cox's method; a conservative method; and a parametric bootstrap method. The simulation study finds that the naive method is inappropriate, that Cox's method has the smallest coverage error for moderate and large sample sizes, and that the bootstrap method has the smallest coverage error for small sample sizes. In addition, Cox's method produces the smallest interval width among the three appropriate methods. We also apply the four methods to a real data set to contrast the differences.

UR - http://www.scopus.com/inward/record.url?scp=0030903159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030903159&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-0258(19970415)16:7<783::AID-SIM488>3.0.CO;2-2

DO - 10.1002/(SICI)1097-0258(19970415)16:7<783::AID-SIM488>3.0.CO;2-2

M3 - Article

C2 - 9131765

AN - SCOPUS:0030903159

VL - 16

SP - 783

EP - 790

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 7

ER -