cccrm (version 1.1)

cccUst: Repeated Measures Concordance Correlation Coefficient estimated by U statistics

Description

Estimates the concordance correlation coefficient for repeated measurements using the U statistics approach. This function is also appropiate for the non-repeated measures setting subject and observer.

Usage

cccUst(dataset,ry,rmet,rtime,Dmat=NULL,delta=1)
## S3 method for class 'default':
cccUst(dataset,ry,rmet,rtime,Dmat=NULL,delta=1)
## S3 method for class 'cccUst':
print(x,...)
## S3 method for class 'cccUst':
summary(object,...)
## S3 method for class 'summary.cccUst':
print(x,...)

Arguments

dataset

Name of data set

ry

Character string indicating the outcome in data set

rmet

Character string indicating the method variable in data set

rtime

Character string indicating the time variable in data set

Dmat

Matrix of weigths

delta

The power of the differences. Delta=0 yields a parameter that is comparable to repeated measures version of kappa

x

Object class cccUst

object

Object class cccUst

...

other arguments to be passed to print or summary

Value

• An object of class cccUst.The generic function print and summary gives the estimates of the concordance correlation coefficient. The object cccUst contains the following components:
• CCC
  Coficient of concordance
• se
  Standard Error of CCC
• low
  Lower limit of the confidence interval ccc
• up
  upper limit of the confidence interval ccc
• Z
  Z trasformation
• seZ
  Standard Error of Z trasformation

References

King, T. S. and Chinchilli, V. M. (2001). A generalized concordance correlation coefficient for continuous and categorical data. Statistics in Medicine 20, 2131 2147. King, T. S., Chinchilli, V. M., Carrasco, J. L. (2007). A repeated measures concordance correlation coefficient. Statistics in Medicine 26(16):3095 3113

Examples

#No Longitudinal dataset
data(bpres)
bp1<-bpres[bpres$NM==1,]

result<-cccUst(bp1,"DIA","METODE")
result

summary(result)

#Longitudinal dataset
data(bdaw)

result2<-cccUst(bdaw,"cort_auc","met","VNUM")
result2

summary(result2)

#Weigthed lognitudinal dataset
data(bfat)

result3<-cccUst(bfat,"bf","met","VISITNO",Dmat=diag(c(2,1,1)))
result3

summary(result3)