Estimation of the concordance correlation coefficient for repeated measures using SAS and R

Josep L. Carrasco, Brenda R. Phillips, Josep Puig-Martinez, Tonya S. King, Vernon M. Chinchilli

Research output: Contribution to journalArticle

58 Scopus citations

Abstract

The concordance correlation coefficient is one of the most common approaches used to assess agreement among different observers or instruments when the outcome of interest is a continuous variable. A SAS macro and R package are provided here to estimate the concordance correlation coefficient (CCC) where the design of the data involves repeated measurements by subject and observer. The CCC is estimated using U-statistics (UST) and variance components (VC) approaches. Confidence intervals and standard errors are reported along with the point estimate of the CCC. In the case of the VC approach, the linear mixed model output and variance components estimates are also provided. The performance of each function is shown by means of some examples with real data sets.

Original languageEnglish (US)
Pages (from-to)293-304
Number of pages12
JournalComputer Methods and Programs in Biomedicine
Volume109
Issue number3
DOIs
StatePublished - Mar 1 2013

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Health Informatics

Fingerprint Dive into the research topics of 'Estimation of the concordance correlation coefficient for repeated measures using SAS and R'. Together they form a unique fingerprint.

  • Cite this