Compartir
Título
Comparing Hierarchical Trees in Statistical Implicative Analysis & Hierarchical Cluster in Learning Analytics
Autor
Facultad/Centro
Área de conocimiento
Asignaturas
ACM International Conference Proceeding Series
Datos de la obra
Pazmiñ o-Maji, R. A., Garcíá-Peñ alvo, F. J., & Conde-González, M. A. (2017). Comparing Hierarchical Trees in Statistical Implicative Analysis & Hierarchical Cluster in Learning Analytics. ACM International Conference Proceeding Series, 2017-January. https://doi.org/10.1145/3144826.3145399
Editor
Association for Computing Machinery
Fecha
2017-10-18
Abstract
[EN] Learning Analytics1 has been and is still an emerging technology in education; the amount of research on learning analysis is increasing every year. The integration of new open source tools, analysis methods, and other calculation options are important. This paper aims to compare hierarchical trees in Statistical Implicative Analysis (SIA) and some hierarchical clusters in Learning Analytics. To this end, we must use a quasi-experimental design with random binary data. A comparison is about the time it takes to evaluate the function for execute the four cluster algorithms: cohesion tree (ASI), similarity tree (ASI), agnes (cluster R package) and hclust (R base function). This paper provides a alternative hierarchical cluster used in Statistical Implicative Analysis that is possible to use in Learning Analytics (LA). Also, provides a comparative R-program used and identifies future research about software performance.
Materia
Palabras clave
URI
Collections
Files in this item
Tamaño:
861.0
xmlui.dri2xhtml.METS-1.0.size-kilobytes
Formato:
Adobe PDF