Visualizing and Understanding Large-Scale Assessments in Mathematics through Dimensionality Reduction
In this paper, we apply the Logistic PCA (LPCA) as a dimensionality reduction tool for visualizing patterns and characterizing the relevance of mathematics abilities from a given population measured by a large-scale assessment. We establish an equivalence of parameters between LPCA, Inner Product Representation (IPR) and the two paramenter logistic model (2PL) from the Item Response Theory (IRT). This equivalence provides three complemetary ways of looking at data that assists professionals in education to perform in-context interpretations. Particularly, we analyse the data collected from SPAECE, a large-scale assessment in Mathematics that has been applied yearly in the public educational system of the state of Ceará, Brazil. As the main result, we show that the the poor performance of examinees in the end of middle school is primarily caused by their disabilities in number sense.