Over the last decade, the assessment of university teaching quality has assumed a prominent role in the university system with the main purpose of improving the quality of courses offered to students. As a result of this process, a host of studies on the evaluation of university teaching was devoted to the Italian system, covering different topics and considering case studies and methodological issues. Based upon this debate, the contribution aims to present an integrated strategy of analysis which combines both descriptive and model-based methods for the treatment of student evaluation of teaching data. More specifically, the joint use of item response theory and multilevel models allows, on the one hand, to compare courses’ ranking based on different indicators and, on the other hand, to define a model-based approach for building up indicators of overall students’ satisfaction, while adjusting for their characteristics and differences in the compositional variables across courses. The usefulness and the relative merits of the proposed procedure are discussed within a real data set.

An integrated strategy for the analysis of student evaluation of teaching: from descriptive measures to explanatory models

SULIS, ISABELLA;
2017

Abstract

Over the last decade, the assessment of university teaching quality has assumed a prominent role in the university system with the main purpose of improving the quality of courses offered to students. As a result of this process, a host of studies on the evaluation of university teaching was devoted to the Italian system, covering different topics and considering case studies and methodological issues. Based upon this debate, the contribution aims to present an integrated strategy of analysis which combines both descriptive and model-based methods for the treatment of student evaluation of teaching data. More specifically, the joint use of item response theory and multilevel models allows, on the one hand, to compare courses’ ranking based on different indicators and, on the other hand, to define a model-based approach for building up indicators of overall students’ satisfaction, while adjusting for their characteristics and differences in the compositional variables across courses. The usefulness and the relative merits of the proposed procedure are discussed within a real data set.
IRT model; Multilevel model; Ordinal data; Students’ ratings; Teaching evaluation; Statistics and probability; Social sciences (all)
File in questo prodotto:
File Dimensione Formato  
Sulis2017_lppsv.pdf

Solo gestori archivio

Tipologia: versione editoriale
Dimensione 709.77 kB
Formato Adobe PDF
709.77 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Quality&Quantity_Sulis.pdf

accesso aperto

Tipologia: versione post-print
Dimensione 1.13 MB
Formato Adobe PDF
1.13 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11584/188950
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 8
social impact