Predicting dropout in Higher Education across borders

ABSTRACT

Study success in Higher Education is of primary importance in the European policy agenda. Yet, given the diverse educational landscape across countries and institutions, more coordinated action is needed to gain a more solid knowledge of the dropout phenomenon. This study aims to gain a better insight into students’ dropout based on an integrated comparative study of two universities located in two different European countries: Politecnico di Milano (Italy) and Vrije Universiteit Amsterdam (the Netherlands). This research aims at assessing whether the factors affecting dropout are similar in the Italian and the Dutch contexts by testing the predictive capacity of ad-hoc models trained in other university-country settings at three different stages of the student’s university journey: (i) enrolment, (ii) end of the first semester, and (iii) end of the first year. Results show that the predictive capacity of models is exchangeable across different contexts, and it improves dramatically once data on university performance becomes available. We find that the models trained in the Dutch context have a better ability to identify dropouts in the Italian context than the other way around. Models trained on Dutch data allow us to better understand the relationship between educational credits obtained, the most important variable across models, and students’ dropout. This study contributes to creating a European common arena for discussing Higher Education success issues.

KEYWORDS:

• Student dropout
• Higher Education
• predictive modeling
• cross-country comparison
• model exchangeability

Acknowledgements

We thank the ‘Data Analytics for Institutional Support’ of PoliMi and ‘Student en Onderwijszaken’ of the Vrije Universiteit Amsterdam for facilitating access to the University register data, and for overall support throughout the research process. These institutional units leverage the available (administrative) datasets of each university to support internal decision-making. All the eventual errors are our sole responsibility.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been corrected with minor changes. These changes do not impact the academic content of the article.

Notes

1 In both countries, students of upper secondary education must select a track that may either be preparatory (i.e. preparing students for tertiary education) and/or terminal (i.e. preparing the students for entry directly into working life).

2 Models trained with different data partitions (70%–30%; 90%–10%) have been added in the Annex B of supplementary material as a robustness test. The results obtained are like the ones obtained with the partition used in the main results.

3 The estimated coefficients on variables in the GLM should be interpreted with caution, due to potential endogeneity concerns. However, it is worth noting that these concerns do not diminish the overall model fit or the validity of model predictions, as explained in (Gujarati 2003). Therefore, there is no need to make any adjustments to the primary metrics of interest in this study.

4 According to the OECD (2022), in Italy 88% of students enrolled in upper secondary vocational programs are enrolled in programs providing access to tertiary education, while only 52% of the students enrolled in upper secondary vocational programs in the Netherlands are in programs that provide access to tertiary education.

5 The Bologna Process is an intergovernmental higher education reform process including 49 European countries and aiming to create comparable HE structures within the European Higher Education Area (European Education and Culture Executive Agency, 2020)