KIT | KIT-Bibliothek | Impressum | Datenschutz

Predictive Modelling of Evidence Informed Teaching

Zhang, Dell; Brown, Chris

In this paper, we analyse the questionnaire survey data collected from 79 English primary schools about the situation of evidence informed teaching, where the evidences could come from research journals or conferences. Specifically, we build a predictive model to see what external factors could help to close the gap between teachers’ belief and behaviour in evidence informed teaching, which is the first of its kind to our knowledge. The major challenge, from the data mining perspective, is that the Likert scale responses are neither categorical nor metric, but actually ordinal, which requires special consideration when we apply statistical analysis or machine learning algorithms. Adapting Gradient Boosted Trees (GBT), we have achieved a decent prediction accuracy with Mean Absolute Error (MAE) 0.36 and gained new insights into possible interventions for promoting evidence informed teaching.

Volltext §
DOI: 10.5445/KSP/1000058749/15
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Informationswirtschaft und Marketing (IISM)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2017
Sprache Englisch
Identifikator ISSN: 2363-9881
KITopen-ID: 1000069934
Erschienen in Archives of Data Science, Series A (Online First)
Band 2
Heft 1
Seiten 15 S. online
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page