Sources of Variation | SS | df | MS | EMS = σ^{2} | ICC/Proportion |
---|---|---|---|---|---|

ICC = method agreement = proportion of patient VC to the total amount of patient VC plus the patient-by-method VC, | |||||

or: ICC = σ^{2}_{P}/(σ^{2}_{P} + σ^{2}_{P × M}) | |||||

For ECW: σ^{2}_{P} = (MS_{P} - MS_{P × M})/2 | |||||

σ^{2}_{M} = (MS_{M} - MS_{P × M})/72 | |||||

σ^{2}_{P × M} = MS_{P × M} | |||||

SDD = smallest detectable difference; with two repeated measurements and a probability of 95% | |||||

SDD = √MS_{P × M} × √2 × 1.96 | |||||

For ECW: SDD = 3.55, so with a probability of 95% score differences lie between -6.8 and 0.3. | |||||

“Limits of agreement” are almost equivalent to SDD limits. Factor “patients” is considered to be a “random” factor, the factor “method” is fixed. | |||||

^{a}SS, sums of squares; MS, mean sum of squares; df, degrees of freedom; EMS, σ^{2} = expected mean sum of squares = (estimated) variance component (VC); ICC, intraclass correlation coefficient. | |||||

Patients (P) | 1396.83 | 71 | 19.67 | 9.02 | 0.846 |

Method (M) | 379.76 | 1 | 379.76 | (5.25) | |

P × M (error) | 116.48 | 71 | 1.64 | 1.64 | 0.154 |

Total | 143 | 10.66 | 1.000 |