作者: Henk Kelderman
DOI: 10.1177/014662169602000205
关键词:
摘要: Rasch models for partial-credit scoring are discussed and a multidimensional version of the model is formu lated. A may be specified in which consecutive item responses depend on an underlying latent trait. In model, different re sponses explained by traits. Data from van Kuyk's (1988) size concept test Raven Progressive Matrices were analyzed. Maximum likelihood estimation goodness-of-fit testing dis cussed applied to these datasets. Goodness-of-fit statistics show that both tests, par tial-credit more appropriate than unidi mensional model.