scholarly journals A Multinomial and Predictive Analysis of Factors Associated with University Dropout

2018 ◽  
Vol 23 (1) ◽  
Author(s):  
Tatiana Fernández-Martín ◽  
Martín Solís-Salazar ◽  
María Teresa Hernández-Jiménez ◽  
Tania Elena Moreira-Mora
Keyword(s):  
Social Impact ◽  
Machine Learning Algorithms ◽  
Dropping Out ◽  
Multinomial Regression ◽  
Study Program ◽  
First Semester ◽  
Student Dropout ◽  
Academic History ◽  
And Performance ◽  
University Dropout

The phenomenon of dropout, by its complexity and educational and social impact, has been extensively studied to understand the specific causes. In this line of research, the purpose of this study was to analyze explanatory and predictive models of student dropout from university studies at the Instituto Tecnológico de Costa Rica (TEC), based on many variables recorded in the institutional system indicators. The first stage of the analysis considered multinomial regression models to identify the influence of these variables on the dropout. In the second analysis, six machine learning algorithms were evaluated in order to find a model that would predict student dropout. Data analysis showed that the probability of dropping out is related to sociodemographic variables, study program, academic history, scholarship and other benefits, and performance after first semester. In addition, the best predictor of dropout algorithm was the “random forest”, a probability of 0.83 to predict the dropout correctly and to capture 34% of the actual student dropout. These results are the first step toward building a more robust predictive model of dropout, which will contribute to preventive decision making in this university.

scholarly journals Review of some studies on university student dropout in Colombia and Latin America

2013 ◽  
Vol 23 (4) ◽  
pp. 37-46
Author(s):  
Luceli Patiño de Peña ◽  
Angélica María Cardona Pérez
Keyword(s):  
Latin America ◽  
Secondary Education ◽  
Research Paper ◽  
University Student ◽  
Dropping Out ◽  
Paper Study ◽  
Education Policies ◽  
Pedagogical Strategies ◽  
Student Dropout ◽  
University Dropout

A study was developed from the research paper Study of academic mortality, pedagogical strategies, and dropout on dropout levels in Colombia and Latin America in order to identify factors that in some way affect increased dropout, such as admissions exams, vocational guidance, economics, and personal difficulties. We also identified the elements of greatest convergence: causes of dropping out, economic difficulties, students’ personal and family histories, secondary education, and, to a lesser degree, suggested strategies that can be used by universities. Therefore, we can conclude that despite the great diversity of studies, the shortcoming lies in the lack of effective policies curtailing university dropout and lack of support for regional education policies to integrate university, society and State.

scholarly journals Early Dropout Prediction Model: A Case Study of University Leveling Course Students

2020 ◽  
Vol 12 (22) ◽  
pp. 9314 ◽  
Author(s):  
Iván Sandoval-Palis ◽  
David Naranjo ◽  
Jack Vidal ◽  
Raquel Gilar-Corbi
Keyword(s):  
Neural Network ◽  
Early Stage ◽  
Activation Function ◽  
Dropping Out ◽  
Student Dropout ◽  
The Neural Network ◽  
Early Dropout ◽  
Substantial Investment ◽  
University Dropout ◽  
National Governments

The school-dropout problem is a serious issue that affects both a country’s education system and its economy, given the substantial investment in education made by national governments. One strategy for counteracting the problem at an early stage is to identify students at risk of dropping out. The present study introduces a model to predict student dropout rates in the Escuela Politécnica Nacional leveling course. Data related to 2097 higher education students were analyzed; a logistic regression model and an artificial neural network model were trained using four variables, which incorporated student academic and socio-economic information. After comparing the two models, the neural network, with an experimentally defined architecture of 4–7–1 architecture and a logistic activation function, was selected as the model that should be applied to early predict dropout in the leveling course. The study findings show that students with the highest risk of dropping out are those in vulnerable situations, with low application grades, from the Costa regime, who are enrolled in the leveling course for technical degrees. This model can be used by the university authorities to identify possible dropout cases, as well as to establish policies to reduce university dropout and failure rates.

scholarly journals Determinants of University Dropout: A Case of Thailand

2019 ◽  
Vol 15 (7) ◽  
pp. 49
Author(s):  
Kelzang Tentsho ◽  
Rhysa McNeil ◽  
Phattrawan Tongkumchum
Keyword(s):  
Logistic Regression Model ◽  
Dropout Rate ◽  
Educational Institutions ◽  
First Semester ◽  
Explanatory Variables ◽  
Student Dropout ◽  
Prince Of Songkla University ◽  
The World ◽  
Admission Type ◽  
University Dropout

Student dropout is a growing concern for educational institutions across the world and extensive research on this issue has been done in past few decades. In this study, we analyzed the determinants of student propensity to dropout at Prince of Songkla University, Pattani campus. The data comprised 10,377 students enrolled between the 2007 and 2011 academic years. Variables included in the analysis were admission year, faculty, gender-religion, first semester GPA and admission type. The overall dropout rate over the five-year period was 23.9%, and a decreasing trend in dropout rate was found from second semester and onwards. A logistic regression model was used to determine the effect of explanatory variables on dropout. The findings indicate that admission year, gender-religion, faculty and first semester GPA are strongly associated with student dropout.

scholarly journals THE USE OF DRILL TECHNIQUES IN TEACHING PRESENT AND PAST TENSE PRIVATE GRAMMAR TOWARD STUDENTS IN ENGLISH STUDY PROGRAM OF UNIMA

2019 ◽  
Vol 4 (1) ◽  
Author(s):  
Fivy Fivy Andries
Keyword(s):  
English Language ◽  
Average Score ◽  
Past Tense ◽  
Study Program ◽  
First Semester ◽  
Class A ◽  
Class B ◽  
Post Test ◽  
Quasi Experimental ◽  
And Performance

This study intends to describe the used of drill techniques can improve understanding and the ability of students to use Simple present and past tense. This research can be classified into quasi-experimental research using the pre-test and post-test design. The research was conducted at the beginning of semester in 2018/2019 academic in year in the first semester, class A amounted to 45 students as the experimental class and class B which amounted to 45 students as a control class. The data were collected through a test. The result showed that the use of drill techniques has been able improve student competence and English performance. The average score of the post test (74) is higher than the pre-test(51.92), and the percentage of student whose grades are 71-100 is 100% while in the pre-test only 18,51%. The researcher came to the conclusion that it was proven, drill techniques can be used as a technique in teaching English to improve the competence and performance of English language students. Keywords: Drill technique, simple present, simple past

Theoretizing A New Sustainable Business Event: Extension of Mair and Jago Model

2015 ◽  
Vol 3 (2) ◽  
pp. 55
Author(s):  
Norol Hamiza Zamzuri ◽  
Khairil Wahidin Awang ◽  
Yuhanis Abdul Aziz ◽  
Zaiton Samdin
Keyword(s):  
Social Impact ◽  
Geographical Area ◽  
Infrastructure Development ◽  
Structured Interviews ◽  
Sustainable Business ◽  
Knowledge Resources ◽  
Business Events ◽  
And Performance ◽  
Event Based

The growth of the event sector is underpinned by the demand of organizing a business event.  Thus, it leads to an increase in economic and social impact. However, the problems from the growth of this sector potentially results from the use of several event materials, transportation and infrastructure development.  Organizing a green event is seen as one of the strategies to reduce the environmental impact.  Therefore, the aim of this paper is to explore the issues involved throughout the process of greening an event by applying Mair and Jago Model.  Semi-structured interviews were conducted with event managers from six Malaysia business event companies that encourage green practices during their event.  Findings suggest that impact, initiative, support and performance motivates event organizers in organizing a green event.  It has also been found that knowledge, resources and behaviour are the barriers faced by event organizers throughout the process of organizing a green event.  Based on the findings it appears that two important factors have emerged from the data collection and analysis that showed a deviation from the Mair and Jago Model, namely “impact” for the motivation element and “support” for the barrier element.  The main limitation of this study was the scope of the study; as it only focuses on business events.  However, as the main purpose of this study is to explore the issues of organizing a green event, it has been found that there are other issues need to be explored in other contexts and geographical area.  Apart from this, as this is a case study, it can only replicate according to the circumstances of this case study. However, this study can be generalized in terms of the theory that has emerged from it.  It is suggested that further research should explore more issues in other contexts and geographical areas. 

Disposisi Matematis Dan Kemandirian Belajar Mahasiswa Pada Perkuliahan Daring Berbantuan Google Classroom Masa Covid-19

2020 ◽  
Vol 7 (2) ◽  
pp. 53-64
Author(s):  
Rizki Nurhana Friantini ◽  
Rahmat Winata
Keyword(s):  
Sampling Method ◽  
Female Students ◽  
Male Students ◽  
Study Program ◽  
Male And Female ◽  
First Semester ◽  
Self Regulated Learning ◽  
Online Lectures ◽  
Regulated Learning ◽  
Very High

This study aims to analyze the mathematical disposition and self-regulated learning of online lectures with the help of Google Classroom. This type of research is descriptive quantitative. This study's subjects were 34 students of the first semester of the Mathematics Education Study Program consisting of 11 male students and 23 female students determined by the saturated sampling method. From the research results, it can be concluded that students' mathematical disposition through learning assisted by Google Classroom has high criteria. The mathematical disposition of male and female students through learning assisted by Google Classroom has high criteria. Still, the level of mathematical disposition of male students is slightly higher than female students. Meanwhile, student self-regulated learning with the help of Google Classroom obtains very high criteria. For male and female students, both have very high learning independence criteria in carrying out learning with the help of Google Classroom.Keywords: Mathematical Disposition, Self-regulated learning, Google Classroom, Online Lectures, Gender

scholarly journals Early Dropout Prediction in MOOCs through Supervised Learning and Hyperparameter Optimization

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1701
Author(s):  
Theodor Panagiotakopoulos ◽  
Sotiris Kotsiantis ◽  
Georgios Kostopoulos ◽  
Omiros Iatrellis ◽  
Achilles Kameas
Keyword(s):  
Online Education ◽  
Online Courses ◽  
Early Stage ◽  
Activity Patterns ◽  
Daily Basis ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Educational Institutions ◽  
Student Dropout ◽  
Wide Range

Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the field of online education. Students with different needs and learning specificities are able to attend a wide range of specialized online courses offered by universities and educational institutions. As a result, large amounts of data regarding students’ demographic characteristics, activity patterns, and learning performances are generated and stored in institutional repositories on a daily basis. Unfortunately, a key issue in MOOCs is low completion rates, which directly affect student success. Therefore, it is of utmost importance for educational institutions and faculty members to find more effective practices and reduce non-completer ratios. In this context, the main purpose of the present study is to employ a plethora of state-of-the-art supervised machine learning algorithms for predicting student dropout in a MOOC for smart city professionals at an early stage. The experimental results show that accuracy exceeds 96% based on data collected during the first week of the course, thus enabling effective intervention strategies and support actions.

scholarly journals Automatic Promotion and Student Dropout: Evidence from Uganda, Using Propensity Score in Difference in Differences Model

2018 ◽  
Vol 7 (2) ◽  
pp. 191 ◽  
Author(s):  
Jeje Moses Okurut
Keyword(s):  
Propensity Score ◽  
Dropping Out ◽  
Probit Regression ◽  
Difference In Differences ◽  
Student Dropout ◽  
Analysis Technique ◽  
Analysis Strategy ◽  
Negative Effect ◽  
And Control ◽  
The Impact

The impact of automatic promotion practice on students dropping out of Uganda’s primary education was assessed using propensity score in difference in differences analysis technique. The analysis strategy was instrumental in addressing the selection bias problem, as well as biases arising from common trends over time, and permanent latent differences between the treated and control groups. Probit regression results indicate a negative effect on the probability of students dropping out, but only at P3. There seems to be no policy effect at P6. Decomposing the effect incidence along school location shows the policy as having had an effect only on P3 students studying in urban schools; otherwise, there is no effect among students at P3 rural, P6 rural or P6 Urban. In terms of the gender component, automatic promotion appears to have had an effect on P3 male and female students and no effect on either sex at P6.

scholarly journals SELF EFFICACY, COPING STRESS DAN PRESTASI AKADEMIK MAHASISWA PROGRAM STUDI PSIKOLOGI FAKULTAS KEDOKTERAN UNIVERSITAS LAMBUNG MANGKURAT

Jurnal Ecopsy ◽  
2016 ◽  
Vol 1 (1) ◽  
Author(s):  
Dwi Nur Rachmah
Keyword(s):  
College Student ◽  
Self Efficacy ◽  
High Performance ◽  
Sampling Technique ◽  
Study Program ◽  
Purposive Sampling ◽  
First Semester ◽  
Stress Scale ◽  
And Coping ◽  
The Relationship

Penelitian ini bertujuan untuk mengetahui gambaran dan hubungan self efficacy, coping stress dan prestasi akademik mahasiswa semester awal Program Studi Psikologi Fakultas Kedokteran Universitas Lambung Mangkurat. Subjek penelitian berjumlah 60 orang. Tekhnik pengambilan data dengan cara purposive sampling. Alat pengumpul data yang digunakan adalah skala self efficacy dan skala coping stress. Untuk prestasi akademik data dikumpulkan dengan melihat indeks prestasi akademik (IPK) semester pertama. Data yang terkumpul dianalisis dengan analisis regresi berganda. Hasil penelitian menunjukkan : (1) tidak ada hubungan yang sangat signifikan antara variabel self efficacy, coping stress dan prestasi akademik , (2) sumbangan prediktor (R2) self efficacy dan coping stress sebesar  2%, (3) rata-rata mahasiswa Program Studi Psikologi angkatan 2012 memiliki self efficacy yang tergolong tinggi, coping stress yang tergolong sedang dan prestasi akademik yang tergolong sedang.Kata kunci : self efficacy, coping stress, dan prestasi akademik  Aim to determine relationship between self efficacy, coping stress and achievement academic in first semester college student of Psychology Study Program of Medical Faculty of Lambung Mangkurat University. Method respondents as many as 60 first semester college students. Sampling technique by using purposive sampling. Data collection by using self efficacy scale, coping of stress scale and achievement academic indeks of first semester. Data analyzed by multiple regression. Results the relationship between self efficacy, coping of stress and achievement academic is not significant.. Self efficacy and coping of stress contribute 2% to achievement academic. Conclusion Odd semester college student in 2012 has high performance in self efficacy, middle in coping of stress and middle in achievement academic. Keywords: self efficacy, coping of stress, achievement academic  

Sign in / Sign up

Export Citation Format

Share Document