Early-predicting dropout of university students: an application of innovative multilevel machine learning and statistical techniques

Cannistrà, Marta; Masci, Chiara; Ieva, Francesca; Agasisti, Tommaso; Paganoni, Anna Maria

doi:10.1080/03075079.2021.2018415

Cited by 21 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Italian Higher Education (HE) system measures a high level of dropout, with many students abandoning their studies during the Bachelor (Cannistrà et al, 2021;Pellagatti et al, 2021). Data from the Annual activity report of Eurostat 2020(EUROSTAT, 2020 show that the educational attainment at the overall tertiary level is very low compared to most of the rest of EU countries.…”

Section: Introductionmentioning

confidence: 99%

“…Dropout has been broadly studied in the literature (Aljohani, 2016;Contini, 2018;Tinto, 1975), with various sources of data and methodological approaches, mainly focused on the classification of dropout (Aljohani, 2016;Cannistrà et al, 2021;Larrabee Sønderlund et al, 2019;Viberg et al, 2018). In the last decades, some researchers have moved to a survival analysis approach (Kleinbaum & Klein, 2004), taking account and modelling the dropout timing (Ameri et al, 2016), being the student dropout the event of interest.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Survival Models for Predicting Student Dropout at University Across Time

Masci¹,

Giovio²,

Mussida³

2022

Education and New Developments 2022 – Volume I

Self Cite

View full text Add to dashboard Cite

"The aim of this study is to develop a tool to recognize major responsible factors of student dropout through time, both in terms of student characteristics and type of degree courses, and to accurately predict the student time to dropout, if any. From a predictive point of view, we aim at developing an early warning system to early predict the status of a student career, identifying the risky timings in terms of dropout, as a supporting tool for early interventions policies. To this end, we follow a Survival Analysis approach, applying time-dependent COX frailty models, in which the target variable is the time to dropout of students within the first three years after the enrolment. Student careers are tracked over time, collecting time-dependent information. Results show that first year information is already powerfully predictive of the time to dropout and that dropout trends differ across degree courses and student profiles."

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Survival Models for Predicting Student Dropout at University Across Time

Masci¹,

Giovio²,

Mussida³

2022

Education and New Developments 2022 – Volume I

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Education and New Developments 2022 – Volume I

2022

View full text Add to dashboard Cite

This book contains the full text of papers and posters presented at the International Conference on Education and New Developments (END 2022), organized by the World Institute for Advanced Research and Science (WIARS).Education, in our contemporary world, is a right since we are born. Every experience has a formative effect on the constitution of the human being, in the way one thinks, feels and acts. One of the most important contributions resides in what and how we learn through the improvement of educational processes, both in formal and informal settings. The International Conference seeks to provide some answers and explore the processes, actions, challenges and outcomes of learning, teaching and human development. The goal is to offer a worldwide connection between teachers, students, researchers and lecturers, from a wide range of academic fields, interested in exploring and giving their contribution in educational issues. We take pride in having been able to connect and bring together academics, scholars, practitioners and others interested in a field that is fertile in new perspectives, ideas and knowledge.We counted on an extensive variety of contributors and presenters, which can supplement our view of the human essence and behavior, showing the impact of their different personal, academic and cultural experiences. This is, certainly, one of the reasons we have many nationalities and cultures represented, inspiring multi-disciplinary collaborative links, fomenting intellectual encounter and development.END 2022 received 790 submissions, from more than 45 different countries, reviewed by a double-blind process. Submissions were prepared to take form of Oral Presentations, Posters, Virtual Presentations and Workshops. The conference accepted for presentation 263 submissions (33% acceptance rate), from which, 233 submissions are published in full text in these volumes.

show abstract

“…This work is within the SPEET project and focuses on the analysis of data about Politecnico di Milano (PoliMI) students attending Bachelor courses in engineering. The PoliMI dropout rate in engineering is around 30%, with the majority of students dropping out during the first year (Cannistrà et al (2021)). This high percentage represents a net waste of resources, since educating students is a costly activity that generates returns in the long term.…”

mentioning

confidence: 99%

“…In this perspective, concluded careers of students can be classified as graduate, early dropout (i.e., careers concluded with a dropout within the first three semesters since the enrolment) and late dropout (i.e., careers concluded with a dropout after more than three semesters since the enrolment). Studies confirm that the causes and dynamics of these two types of dropout might be different, and their distinction and identification is essential in the perspective of supporting students at-risk (Cannistrà et al (2021)).…”

mentioning

confidence: 99%

Semiparametric multinomial mixed-effects models: A university students profiling tool

2022

Self Cite

View full text Add to dashboard Cite

Many applicative studies deal with multinomial responses and hierarchical data. Performing clustering at the highest level of grouping, in multilevel multinomial regression, is also often of interest. In this study we analyse Politecnico di Milano data with the aim of profiling students, modelling their probabilities of belonging to different categories and considering their nested structure within engineering degree programmes. In particular, we are interested in clustering degree programmes standing on their effects on different types of student career. To this end, we propose an EM algorithm for implementing semiparametric mixed-effects models dealing with a multinomial response. The novel semiparametric approach assumes the random effects to follow a multivariate discrete distribution with an a priori unknown number of support points, that is, allowed to differ across response categories. The advantage of this modelling is twofold: the discrete distribution on random effects allows, first, to express the marginal density as a weighted sum, avoiding numerical problems in the integration step, typical of the parametric approach, and, second, to identify a latent structure at the highest level of the hierarchy where groups are clustered into subpopulations.

show abstract

Early-predicting dropout of university students: an application of innovative multilevel machine learning and statistical techniques

Cited by 21 publications

References 41 publications

Survival Models for Predicting Student Dropout at University Across Time

Survival Models for Predicting Student Dropout at University Across Time

Education and New Developments 2022 – Volume I

Semiparametric multinomial mixed-effects models: A university students profiling tool

Contact Info

Product

Resources

About