Hypotheses for Attribute Agreement Analysis

For an attribute agreement analysis, you test agreement by looking at the p-values for kappa statistics and Kendall's coefficients.

Hypotheses for Kappa

For Within Appraiser, the hypotheses to test for agreement are:

For Each Appraiser vs Standard, the hypotheses to test for agreement are:

H₀: the agreement between appraisers' ratings and the standard is due to chance.
H₁: the agreement between appraisers' ratings and the standard is not due to chance.

For Between Appraisers, the hypotheses to test for agreement are:

For All Appraisers vs Standard, the hypotheses to test for agreement are:

H₀: the agreement between appraisers' ratings and the standard is due to chance.
H₁: the agreement between appraisers' ratings and the standard is not due to chance.

For Within Appraiser, the hypotheses to test for agreement are:

For Each Appraiser vs Standard, the hypotheses to test for agreement are:

For Between Appraisers, the hypotheses to test for agreement are:

For All Appraisers vs Standard, the hypotheses to test for agreement are:

H₀: there is no association between ratings of all appraisers and the known standard.
H₁: the ratings by all appraisers are associated with the known standard.