A. Agresti, LOGIT-MODELS AND RELATED QUASI-SYMMETRICAL LOG-LINEAR MODELS FOR COMPARING RESPONSES TO SIMILAR ITEMS IN A SURVEY, Sociological methods & research, 24(1), 1995, pp. 68-95
Suppose that subjects respond to a battery of questions (items) of a s
imilar nature in a survey, with each item having the same categorical
scale. This article discusses models that express logits for the respo
nse distributions in terms of subject and item effects. The models, wh
ich generalize the Rasch model, have interpretations referring to subj
ect-specific comparisons of the items. Recent literature shows that on
e can estimate item parameters using estimates of main effect paramete
rs in corresponding quasi-symmetric log-linear models. We discuss this
connection giving primary attention to ordinal response models using
adjacent-category logits and cumulative logits. For the case of two it
ems, we give expressions for models and corresponding parameter estima
tes that are the basis of simple tests of marginal homogeneity for squ
are ordinal contingency tables.