Nonparametric cognitive diagnosis of profiles of mathematical knowledge of teacher education candidates

Traditionally, the selection process of teacher candidates has emphasized the assessment of subject matter and pedagogical knowledge using psychometric methodologies, which simply organize candidates in continuous scales and require a large number of samples. However, these methods do not allow for the identification of candidates' knowledge profiles and learning paths, which would help develop programs tailored to support students in their training process. In this study, an evaluation instrument was developed by using the nonparametric approach to model diagnostic classifications and was then validated on a sample of 119 participants. This instrument allows for disaggregating candidates' initial knowledge and establishing relationships between its components. The results showed that candidates present a variety of profiles, which may consider more than one attribute. Not only does it provide a score that can be used for selection processes, it also provides useful information for initial teacher training methods.