ANOTHER INTERPRETATION OF A MODEL FOR PAIRED COMPARISONS.
Technical rept. no. 14 (Statistics rept.),
FLORIDA STATE UNIV TALLAHASSEE
Pagination or Media Count:
The first effect of this paper is to demonstrate that the paired comparisons model may be derived from a variety of different initial assumptions about the nature of paired comparisons, some of these assumptions appearing to be more appropriate to a description of the preferencedecision process than others. The second effect of this paper is to note that the generalization of the model to triple comparisons chosen earlier is not the one compatible with the Lehmann model even though it seems to possess other desirable properties. Limited numerical calculations suggest that both models for triple comparisons give comparable results in applications and their asymptotic properties should be similar. Author