Comparison of concordance correlation coefficient estimating approaches with skewed data

Josep L. Carrasco, Lluis Jover, Tonya King, Vernon Chinchilli

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

The concordance correlation coefficient (CCC) is an index that assesses the agreement between continuous measures made by different observers. At least four methods are used to estimate the CCC: two (Lin's method, Variance Components) which are defined on the basis that data are normally distributed, and the two others (U-statistics, GEE) which do not assume any particular distribution of the data. Here the four methods are compared with skewed data from a model in which the subject means follow a log-normal distribution while the within-subject variability is assumed to be normally distributed. An example of alcohol consumption is considered and a simulation study is performed.

Original languageEnglish (US)
Pages (from-to)673-684
Number of pages12
JournalJournal of Biopharmaceutical Statistics
Volume17
Issue number4
DOIs
StatePublished - Jul 1 2007

Fingerprint

Concordance
Correlation coefficient
U-statistics
Variance Components
Log Normal Distribution
Normal Distribution
Alcohol
Alcohol Drinking
Observer
Simulation Study
Estimate
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Pharmacology
  • Pharmacology (medical)

Cite this

@article{1fa91e03d30d4048b2175e631e55b823,
title = "Comparison of concordance correlation coefficient estimating approaches with skewed data",
abstract = "The concordance correlation coefficient (CCC) is an index that assesses the agreement between continuous measures made by different observers. At least four methods are used to estimate the CCC: two (Lin's method, Variance Components) which are defined on the basis that data are normally distributed, and the two others (U-statistics, GEE) which do not assume any particular distribution of the data. Here the four methods are compared with skewed data from a model in which the subject means follow a log-normal distribution while the within-subject variability is assumed to be normally distributed. An example of alcohol consumption is considered and a simulation study is performed.",
author = "Carrasco, {Josep L.} and Lluis Jover and Tonya King and Vernon Chinchilli",
year = "2007",
month = "7",
day = "1",
doi = "10.1080/10543400701329463",
language = "English (US)",
volume = "17",
pages = "673--684",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

Comparison of concordance correlation coefficient estimating approaches with skewed data. / Carrasco, Josep L.; Jover, Lluis; King, Tonya; Chinchilli, Vernon.

In: Journal of Biopharmaceutical Statistics, Vol. 17, No. 4, 01.07.2007, p. 673-684.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparison of concordance correlation coefficient estimating approaches with skewed data

AU - Carrasco, Josep L.

AU - Jover, Lluis

AU - King, Tonya

AU - Chinchilli, Vernon

PY - 2007/7/1

Y1 - 2007/7/1

N2 - The concordance correlation coefficient (CCC) is an index that assesses the agreement between continuous measures made by different observers. At least four methods are used to estimate the CCC: two (Lin's method, Variance Components) which are defined on the basis that data are normally distributed, and the two others (U-statistics, GEE) which do not assume any particular distribution of the data. Here the four methods are compared with skewed data from a model in which the subject means follow a log-normal distribution while the within-subject variability is assumed to be normally distributed. An example of alcohol consumption is considered and a simulation study is performed.

AB - The concordance correlation coefficient (CCC) is an index that assesses the agreement between continuous measures made by different observers. At least four methods are used to estimate the CCC: two (Lin's method, Variance Components) which are defined on the basis that data are normally distributed, and the two others (U-statistics, GEE) which do not assume any particular distribution of the data. Here the four methods are compared with skewed data from a model in which the subject means follow a log-normal distribution while the within-subject variability is assumed to be normally distributed. An example of alcohol consumption is considered and a simulation study is performed.

UR - http://www.scopus.com/inward/record.url?scp=34347393272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34347393272&partnerID=8YFLogxK

U2 - 10.1080/10543400701329463

DO - 10.1080/10543400701329463

M3 - Article

C2 - 17613647

AN - SCOPUS:34347393272

VL - 17

SP - 673

EP - 684

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

IS - 4

ER -