Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The expansion of Higher Education increased the diversity of students, with heterogenous characteristics, needs, and values. Institutions, intending to preserve the mission and the transformative potential of the tertiary level of education, are facing and implementing policies and practices that enhance success conditions, persistence, and avoid s...
Contexts in source publication
Context 1
... the gradual dropout process by STEM students can contribute to the better identification of institutional actions to prevent and reduce its occurrence, especially in first-year students. For the reflective construct 'Adaptation difficulties', the moderating variables are illustrated in Figure 1. ...
Context 2
... were analyzed using the statistical program Stata v.14 [60,61]. The relationships hypothesized in Figure 1 are assessed through structural equation modeling (SEM), and mediation analysis is performed to estimate indirect, direct, and total effects of the potential mediators. Data were analyzed using the statistical program Stata v.14 [62][63][64]. ...
Citations
... A university dropout rate of over 40% in Latin America has been observed (Fonseca-Grandón, 2018). Attrition results from the interaction of factors that negatively influence students not completing their university studies (Casanova et al., 2023). ...
Introduction
University dropouts are a problem in the Chilean higher education system, which causes psychosocial and economic damage and requires further studies to understand it comprehensively. This study aimed to determine the psychosocial variables influencing the risk of dropping out of the higher education system in a sample of Chilean university students post-pandemic.
Methods
With a sample of 655 students from the Chilean higher education system and with a cross-sectional study design taken in November 2022, a questionnaire was applied with sociodemographic and other variables of interest, the Depression, Anxiety and Stress Scale DASS-21, the EAC-19 Coronavirus Affect Scale, the ECE Emotional Exhaustion Scale; the Okasha Suicide Scale, and the Insomnia Severity Index (ISI). We performed descriptive, bivariate, and multiple logistic regression analyses through SPSS version 25. Variables with a value of p <0.05 in the final model were declared statistically significant. Odds ratios (OR) were adjusted to 95% confidence intervals (95% CI), which were used to determine the independent predictor variables.
Results
Significant variables for the risk of dropping out of higher education were: failing four or more courses [AOR = 3.434; 95% CI: 1.272, 9.269], having depressive symptoms [AOR = 1.857; 95% CI: 1.214, 2.839], having suicidal ideation and thoughts [AOR = 2.169; 95% CI: 1.509, 3.118], having clinical insomnia [AOR = 2.024; 95% CI: 1.400, 2.927], low parental support [AOR = 1.459; 95% CI: 1.029, 2.069], impaired performance during the pandemic [AOR = 1.882; 95% CI: 1.317, 2.690], and impaired socioeconomic status during the pandemic [AOR = 1.649; 95% CI: 1.153, 2.357].
Conclusion
Chilean higher education institutions should pay attention to the risk factors resulting from this research, such as students with more than four failed courses during their career, depressive symptoms, suicidal thoughts, clinical insomnia, low parental support, and affectation in performance and socioeconomic level during the pandemic, which could contribute to improving academic retention indicators.
... present a poorer academic background, especially when they have a disadvantaged socioeconomic situation. Without adequate support, these factors can lead students to underperformance, demotivation, academic disengagement and, ultimately, drop out (Casanova et al., 2018(Casanova et al., , 2023. Some of these difficulties can be exacerbated for students of degrees grounded in the areas of mathematics, physics and chemistry, which require a stronger school background (Casanova et al., 2023). ...
... Without adequate support, these factors can lead students to underperformance, demotivation, academic disengagement and, ultimately, drop out (Casanova et al., 2018(Casanova et al., , 2023. Some of these difficulties can be exacerbated for students of degrees grounded in the areas of mathematics, physics and chemistry, which require a stronger school background (Casanova et al., 2023). Degrees in Exact and Earth Sciences fit this case and, not coincidentally, concentrate the highest numbers of dropouts in our analysis. ...
... In such cases, the students' residential environment, with few rooms and demands of domestic activities, may also hinder their study. In this context, financial support policies, which were already important for students' permanence in higher education (Casanova et al., 2023), become essential. We believe that the no change, during the ERL, in the dropout pattern related to family income is related to the implementation of preventive strategies by the IFFar during the pandemic, such as the loan of computer equipment and the provision of emergency aid to students in socio-economic vulnerability (IFFar, 2021). ...
During the COVID‐19 pandemic, the challenges associated with the transition from face‐to‐face to emergency remote education increased concerns about student dropout. Aligned with this concern, this study investigates the impact of the pandemic on the dropout patterns of 3371 undergraduate students from a Brazilian institution. Using data mining and machine learning techniques, we developed predictive dropout models based on student data preceding and succeeding the onset of the pandemic. Through the interpretation and comparison of these models and with the support of statistical and graphical analyses, we identify that the patterns persistently indicate that young students in their initial semesters, characterized by lower income, academic performance, and interaction, remain most susceptible to dropping out. Despite the pandemic leading to an enhanced predictive capability of data regarding student interaction within the virtual learning environment, our analysis revealed a lack of significant variation in dropout patterns. Institutionally, this indicates that a considerable number of dropouts likely encountered challenges in adapting to higher education, both before and throughout the pandemic.
Practitioner notes
What is already known about this topic
The challenges posed by emergency remote learning, implemented during the COVID‐19 pandemic, may exacerbate the dropout problem and change the patterns involved in this phenomenon.
Despite being widely used to identify dropout profiles and/or predict at‐risk students, data mining and machine learning techniques have been little explored in the investigation of changes associated with the pandemic context.
What this paper adds
We employ data mining and machine learning techniques to construct predictive and interpretable dropout models for the pre‐ and during‐pandemic contexts of a Brazilian institution. Comparing these models, we investigate the impacts of the pandemic on dropout patterns.
The pandemic and the shift to emergency remote learning have an enhanced predictive capability of data regarding student interaction within the virtual learning environment.
Throughout the pandemic, there was limited variation observed in dropout patterns, consistently highlighting young students in their initial semesters with lower income, academic performance and levels of interaction.
Implications for practice and/or policy
This study urges the inclusion of interactional student data in future dropout prediction research, capitalizing on the enhanced predictive power attained through the widespread adoption of virtual learning environments.
Institutionally, the dropout patterns from before and during the pandemic suggest that students may be facing difficulties in adapting to higher education. In addition to the need to intensify preventive actions, this work indicates the need to conduct a study specifically targeting first‐semester students to understand their needs better and redesign preventive policies.
University dropout is a phenomenon of growing interest due to its negative consequences. Various variables have been studied in order to understand why this problem occurs. Satisfaction with the degree choice, self-regulation strategies and engagement within the university are some of the variables that have been studied in order to understand why students decide to drop out university. In this sense, it is also important to consider uncertainty, which refers to the level of certainty that students have about these variables to understand the decisions to drop out. Therefore, the aim of this research is to analyse the uncertainty associated with the decision to drop out studies among first year and second-year students, based on these three variables using Multiple Criteria Decision-Making. We performed descriptive analyses and FTOPSIS method on a sample of 719 students from a university in the north of Spain. We saw a relationship between the three variables studied and the intention to persist, as well as being a first-year student. In conclusion, it is important to continue studying the variables that influence this phenomenon in greater depth. In addition , this type of analysis could help in future research to understand in greater depth the influence of other variables on dropout rates.
