LOGLINEAR RASCH MODELS FOR THE ANALYSIS OF STABILITY AND CHANGE

Loglinear unidimensional and multidimensional Rasch models are conside red for the analysis of repeated observations of polytomous indicators with ordered response categories. Reparameterizations and parameter r estrictions are provided which facilitate specification of a variety o f hypotheses about latent processes of change. Models of purely quanti tative change in latent traits are proposed as well as models includin g structural change. A conditional likelihood ratio test is presented for the comparison of unidimensional and multiple scales Rasch models. In the context of longitudinal research, this renders possible the st atistical test of homogeneity of change against subject-specific chang e in latent traits. Applications to two empirical data sets illustrate the use of the models.