Assessment of students' statistical skills
E-learning is increasingly used to support student learning in higher education, facilitating administration of online formative assessments. Although providing diagnostic, actionable feedback is generally more effective, in current practice, feedback is often given in the form of a simple proportion of correctly solved items. This project aims to study and apply psychometric methods to obtain detailed diagnostic information about students’ skills from their item response data in the domain of statistics education. In addition, we aim to study effects of providing such diagnostic feedback on students’ learning processes.
This project is partly conducted in collaboration with Grasple, an online learning platform for mathematics and statistics in higher education. Data is collected from bachelor students in introductory statistics courses at the Faculty of Social and Behavioural Sciences at Utrecht University.
Hypotheses and intended outcomes.
First, it is examined how valid and reliable measurements of students’ conceptual understanding of statistics can be obtained with diagnostic classification models. This information can be presented via learning dashboards to support students in monitoring which knowledge and skills are lacking and in making effective learning choices. The value of this support depends on how it is interpreted and used by the recipient. It is desirable to provide sufficient support to the students who need it, while preventing hindering effects of support for others. We aim to explore interactions between support level and both expertise level and self-regulation skills, and how this affects learning processes.
Possibility for internships, thesis or research.
No.