|
⇤ ← Revision 1 as of 2006-10-24 14:08:57
Size: 680
Comment:
|
Size: 695
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 1: | Line 1: |
| Line 6: | Line 5: |
| ICC = __MS(subjects) – MS(subjects x raters)__ MS(subjects) + (k-1)MS(subjects x raters) |
\[ ICC = \frac{__MS(subjects) – MS(subjects x raters)__} {MS(subjects) + (k-1)MS(subjects x raters)} \] |
An alternative, to the kappa statistic, which uses an analysis of variance output to estimate rater reliability is the intraclass correlation coefficient (ICC).
For a repeated measures anova involving k raters it follows
\[ ICC = \frac{MS(subjects) – MS(subjects x raters)}
- {MS(subjects) + (k-1)MS(subjects x raters)}
\]
Examples of its use in SPSS are given at http://www.nyu.edu/its/statistics/Docs/intracls.html
An overview of approaches to inter rater reliability including the ICC is given by Darroch and McCloud(1986).
Reference:
Darroch JN, McCloud PI (1986) Category distinguishability and observer agreement Australian Journal of Statistics 28 371-88.