Comparative Analysis of Dropout and Student Permanence in Rural Higher Education

Rural origin student representation in health courses at the University of Tasmania: 2011-2020

OBJECTIVE

To describe longitudinal trends in the admission and completion of domestic Tasmanian rural origin students in health courses at the University of Tasmania (UTAS).

METHODS

A retrospective audit of records for all domestic Tasmanian students admitted to, or who completed a health course offered by UTAS between 2011 and 2020 was conducted. Data extracted from student records included gender, age, Indigenous background, rural origin (based on residential address outside of Launceston or Hobart at the time of application), health discipline, year of admission and/or completion. Data were analysed in STATA.

RESULTS

Between 2011 and 2020, 7516 domestic Tasmanian students were admitted to health courses at UTAS, of which 22.6% were rural origin (vs. a rural population of 36.7%). Students admitted were mostly female (77.0%) and studying nursing (51.1%). Rural origin students were more likely to study at the regional campus in Launceston than in Hobart, the capital city (OR, 3.79 [3.4-4.3, p < 0.00]). Over this same period, 5086 students completed a health course. There was little difference in completion rates among regional vs. rural origin students (OR, 1.04 [1.0-1.1, p < 0.00]); however, completion rates decreased with increasing remoteness. Indigenous and male students were less likely to complete than non-Indigenous (OR, 0.73 [0.7-0.8, p < 0.05]) and female students (OR, 0.97 [1.0-1.0, p < 0.05]) respectively.

CONCLUSIONS

Tasmanian rural origin students are admitted to a range of health courses at UTAS and many complete. However, additional measures are needed to attract a greater number of local rural origin students to study health courses and to support them through to course completion.

Prevention and Mitigation of Rural Higher Education Dropout in Colombia: A Dynamic Performance Management Approach

Background: Dropout in higher education is a socio-educational phenomenon that has the scope to limit the benefits of education as well as to widen social disparities. For this reason, governments have implemented various public policies for its prevention and mitigation. However, in rural populations, such policies have proven to be ineffective. The aim of this paper is to simulate public policy scenarios for the treatment of school dropout in rural higher education in Colombia from a Dynamic Performance Management approach. Methodology: To achieve the aim, a parameterised simulation model was designed with data from Colombian state entities in rural higher education. Five simulations were carried out. The analysis of the results was carried out using descriptive statistics and comparison of means using the Wilcoxon Sign Rank statistic. Results: The adoption of such an approach based on simulations suggests that policies to expand the coverage of educational credits and financial support, as well as the addition of a family income subsidy, allow for a reduction in the number of dropouts. Conclusions: A dynamic, data-driven approach can be effective in preventing and mitigating dropout in these areas. It also highlights the importance of identifying the key factors contributing to dropout. The results also suggest that government policies can have a significant impact on school retention in rural areas.

Density-Based Unsupervised Learning Algorithm to Categorize College Students into Dropout Risk Levels

Compliance with the basic conditions of quality in higher education implies the design of strategies to reduce student dropout, and Information and Communication Technologies (ICT) in the educational field have allowed directing, reinforcing, and consolidating the process of professional academic training. We propose an academic and emotional tracking model that uses data mining and machine learning to group university students according to their level of dropout risk. We worked with 670 students from a Peruvian public university, applied 5 valid and reliable psychological assessment questionnaires to them using a chatbot-based system, and then classified them using 3 density-based unsupervised learning algorithms, DBSCAN, K-Means, and HDBSCAN. The results showed that HDBSCAN was the most robust option, obtaining better validity levels in two of the three internal indices evaluated, where the performance of the Silhouette index was 0.6823, the performance of the Davies–Bouldin index was 0.6563, and the performance of the Calinski–Harabasz index was 369.6459. The best number of clusters produced by the internal indices was five. For the validation of external indices, with answers from mental health professionals, we obtained a high level of precision in the F-measure: 90.9%, purity: 94.5%, V-measure: 86.9%, and ARI: 86.5%, and this indicates the robustness of the proposed model that allows us to categorize university students into five levels according to the risk of dropping out.