Shrout and Fleiss (1979) Case 3: 1 - MSE/MSR, for when THESE
raters are the only ones of interest. No rater term appears, so
systematic offsets cost nothing – this is a CONSISTENCY
coefficient, not an agreement one. Two raters differing by a
constant on every target score near 1 here and well below it on
ICC(2,k); both are returned with the measured offset so the choice
is informed rather than habitual.
Usage
morie_psy_icc3k(y, subject, rater)
Arguments
- y
ratings.
- subject, rater
identifiers; a complete crossed design.
Value
list: value (ICC(3,k)), icc_single, icc2k,
max_rater_offset, k, n, MSR, MSC, MSE, case, method.
References
Shrout and Fleiss (1979), Case 3 and Table 4;
McGraw and Wong (1996).
Examples
y <- c(9, 2, 5, 8, 6, 1, 3, 2, 8, 4, 6, 8)
morie_psy_icc3k(y, rep(1:3, each = 4), rep(1:4, 3))$value
#> [1] 0.8914729
