AGREEMENT PLUS DISAGREEMENT MODEL FOR AGREEMENT DATA

In R × R square contingency tables where there is a one to one correspondence between the categories of the row and column variables, the agreement between the row and column classifications is of interest. Several authors modeled agreement in terms of a log-linear representation. We propose a new model by combining the agreement and disagreement models, and applying it to the cross-classification of two neurologist’s rates for 149 MS patients.