Purpose: The main purpose of this study is to evaluate the extent of dropout students and identify the relationship between risk factors of dropout and the survival time of students. Design/methodology/approach: The Kaplan-Meier estimator (KM), also known as the product-limit technique, is a nonparametric model function that is commonly used in…

We propose a novel approach to address the issue of college student attrition by developing a hybrid model that combines a structural neural network with a piecewise exponential model. This hybrid model not only shows the potential to robustly identify students who are at high risk of dropout, but also provides insights into which factors are most…

Purpose: The extant research on student attrition and retention has relied on models that focus on factors over which universities may have limited control and thus not lead to actionable practices. To address this shortcoming, the authors applied organizational support theory (OST) to test the association between students' perceptions of justice,…

This paper explores the factors contributing to high dropout rates in U.S. education, particularly in higher education, where 40% of students leave before completing their degrees. It examines causes such as financial difficulties, mental health issues, and lack of engagement, and discusses strategies to reduce dropouts. Key approaches include…

Schools across Texas are tasked with detailing action plans in support of students identified as at-risk of dropping out (TEA, 2020b). The intent of this study was to learn the perspective of students, identified as at-risk of dropping out, in terms of whether there is a relationship between campus retention/recovery intervention efforts and their…

The tutor's role in enhancing student retention in distance learning is paramount. This study aims to predict retention and not actual retention by investigating how tutoring support predicts student retention in distance learning at the University of Cape Coast in Ghana. Moore Transactional Distance Theory underpinned the theoretical framework of…

We present an educational data analytics case study aimed at the early detection of potential dropout in Computer Engineering studies in Cuba. We have employed institutional data of 456 students and performed several experiments for predicting their permanency into three (promotion, repetition, and dropout) or two classes (promoting, not…

This study examined graduation and persistence among social and behavioral science students at a regional comprehensive university. Hazard analyses identified predictors of student trajectories, times at which predictors were more or less impactful, and interactions between predictors such that particular risk factors were more detrimental for…

Young adult carers are four times more likely than other students to drop out of higher education and are amongst the under-represented and disadvantaged groups targeted in the National Strategy for Access and Student Success in Higher Education in the UK. Non-completion of studies has implications not just for the individuals themselves, but also…

The purpose of this investigation was to develop an ultra-short questionnaire that reliably predicted re-enrollment. Two binary stepwise logistic regressions were performed using re-enrollment status as the criterion. The first regression, conducted with a subsample of 4619 undergraduates, reduced 32 items drawn from the College Persistence…

Retention of students is a problem faced by institutions of higher education around the world. Higher education institutions are required to report retention data to government agencies and they depend on tuition funding more than ever before. Prior research has identified many characteristics that when present, increase the likelihood of early…

We perform two approaches of machine learning, logistic regressions and decision trees, to predict student dropout at the Karlsruhe Institute of Technology (KIT). The models are computed on the basis of examination data, i.e. data available at all universities without the need of specific collection. Therefore, we propose a methodical approach…

College students experiencing psychological distress are at unique risk for negative academic outcomes. The Counseling Center Assessment of Psychological Symptoms-62 (CCAPS-62; Locke et al., 2011) is a multidimensional symptom inventory designed for use in college counseling centers. However, the relationships between the CCAPS-62 and functional…

There is growing evidence that school engagement, or more specifically disengagement, is a key indicator for predicting Early School Leaving. The aim of this article is to explore the impact of secondary schools in student (dis)engagement and subsequent opportunities to succeed in school. Drawing on data from a qualitative study in five secondary…

In this article, we interrogate the policy assumptions underlying a significant South Australian public education re-engagement initiative called Flexible Learning Options, formulated within South Australia's social inclusion policy agenda, beginning in 2006. To this end, we applied Baachi's 'What's the Problem Represented to be?' policy analysis…