The longitudinal concordance correlation

Jun 7, 2019·
Thiago de Paula Oliveira
Thiago de Paula Oliveira
,
Rafael De Andrade Moral
,
John Hinde
,
Silvio Sandoval Zocchi
,
Clarice Garcia Borges Demetrio
· 1 min read
Date
Jun 7, 2019 — Jun 12, 2019
Event
Location

University of Minho

Guimarães,

Abstract:

We present the lcc package, available from the Comprehensive R Archive Network (CRAN). The package implements estimation procedures for the longitudinal concordance correlation (LCC), using fixed effects and variance components estimates from linear mixed models. The LCC is a quantity that measures the extent of agreement between two (or more) methods used to evaluate a response variable of interest and is frequently applied in medicine, pharmacology, and agronomy. The main features of the package are the estimation and inference of the extent of agreement using numerical and graphical summaries. Moreover, our approach presents flexibility in the sense that it accommodates both balanced and unbalanced experimental designs, allows for different within-group error structures, while also allowing for the inclusion of covariates in the linear predictor to control systematic variations in the response. We illustrate our methodology by comparing different methods used to measure the peel colour of fruit as an assessment of ripeness.