Performing Learning Analytics via Generalized Mixed-Effects Trees

43/2018

Performing Learning Analytics via Generalized Mixed-Effects Trees

Sunday 29th July 2018

Fontana, L.; Masci, C.; Ieva, F.; Paganoni, A.M.

Nowadays, the importance of Educational Data Mining and Learning Analytics in higher education institutions is increasingly recognized. The analysis of university careers and of student dropout prediction is one of the most studied topics in the area of Learning Analytics. In the perspective of modeling the student dropout, we propose an innovative statistical method, that is a generalization of mixed-effects trees for a response variable in the exponential family: Generalized Mixed-Effects Trees (GMET). We perform a simulation study in order to validate the performance of our proposed method and to compare GMET to classical models. In the case study, we apply GMET to model Bachelor student dropout in different degree programmes of Politecnico di Milano. The model is able to identify discriminating student characteristics and estimate the degree programme effect on the probability of student dropout.

This report, or a modified version of it, has been also submitted to, or published on
Published: Fontana, L., Masci, C., Ieva, F., Paganoni A.M., Performing Learning Analytics via Generalised Mixed-Effects Trees, Data 2021, 6, 74. https://doi.org/10.3390/data6070074, MDPI