Cargando...
In educational research, a fundamental goal is identifying which skills stu- dents have mastered, which skills they have not, and which skills they are in the process of mastering. As the number of examinees, items, and skills increases, the estimation of even simple cognitive diagnosis models becomes difficult. To address this, we introduce a capability matrix showing for each skill the proportion correct on all items tried by each student involving that skill. We apply variations of common clustering methods to this matrix and discuss conditioning on sparse subspaces. We demonstrate the feasibility and scalability of our method on several simulated datasets and illustrate the difficulties inherent in real data using a subset of online mathematics tutor data. We also comment on the interpretability and application of the results for teachers.
"1. Set the starting cluster centers mg to the corners of the K-dim hyper-cube (2K centers). 2. Create the cluster assignment vector A by assigning each Bi to the closest mg. 3. For all clusters g, if no Bi is assigned to mg, i.e. 4. Alternate between 2) and 3) until the cluster assignment vector A does not change. This flexible k-Means variation allows for empty clusters or fewer clusters than origi- nally requested and removes the constraint that there be one cluster per skill set profile. 3.2 Model-based Clustering. Model-based clustering [3,9] is a parametric statistical approach that assumes: the data X = {x1, x2, ..., xn}, xi ∈
Acerca de este recurso...
Visitas 99
Categorías:
Catálogo integrado en el espacio
0 comentarios
¿Quieres comentar? Regístrate o inicia sesión