Shrout and Fleiss intra-class correlation functions

Source: R/ShroutFleissICC1k.R

The functions ShroutFleissICC1, ShroutFleissICC11 and ShroutFleissICC1k computes the intra-class correlation ICC for a given data frame containing repeated measures in columns cols when the measures are in distinct clusters, identified in column clustercol. See (Shrout and Fleiss 1979) .

ShroutFleissICC1(dta, clustercol, cols)

Arguments

dta

A data frame containing within-subject measures, one participant per line;

clustercol

is the column index where cluster belonging are given;

cols

A vector indicating the columns containing the measures.

Value

ICC the intra-class measure of association.

References

Shrout PE, Fleiss JL (1979). “Intraclass correlations: uses in assessing rater reliability.” Psychological bulletin, 86(2), 420.

Shrout PE, Fleiss JL (1979). “Intraclass correlations: uses in assessing rater reliability.” Psychological bulletin, 86(2), 420.

Examples

# creates a small data frames with 4 subject's scores for 5 measures:
dta <- data.frame(cbind(
        clus <- c(1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3),
        col1 <- c(2, 4, 4, 6, 4, 5, 8, 8, 5, 8, 9, 9)
    ))

ShroutFleissICC1(dta, 1, 2)
#> [1] 0.4343434
# 0.434343434 
ShroutFleissICC11(dta[, 1], dta[,2])
#> [1] 0.4343434
# 0.434343434 

dta2 <- data.frame(cbind(
        clus <- c(1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3),
        col1 <- c(1, 3, 3, 5, 3, 4, 7, 7, 4, 7, 8, 8),
        col1 <- c(2, 4, 4, 6, 4, 5, 8, 8, 5, 8, 9, 9),
        col1 <- c(3, 5, 5, 7, 5, 6, 9, 9, 6, 9, 10, 10)
    ))
 
ShroutFleissICC1(dta2, 1, 2:4)
#> [1] 0.754386
# 0.7543859649 
ShroutFleissICC1k(dta2[, 1], dta2[,2:4])
#> [1] 0.754386
# 0.7543859649