scholarly journals Classification Algorithm Accuracy Improvement for Student Graduation Prediction Using Ensemble Model

Author(s):  
Ace C. Lagman ◽  
◽  
Lourwel P. Alfonso ◽  
Marie Luvett I. Goh ◽  
Jay-ar P. Lalata ◽  
...  

According to National Center for Education Statistics, almost half of the first-time freshmen full time students who began seeking a bachelor’s degree do not graduate. The imbalance between

2015 ◽  
Vol 2 ◽  
pp. 104-110
Author(s):  
Ace C. Lagman

Logistic regression is a predictive modeling technique that finds an association between the independent variables and the logarithm of the odds of a categorical response variable. This is one of the techniques used in analyzing a categorical dependent variable. The study focused on the application of logistic regression in predicting student graduation by generating data models that could early predict and identify students who are prone to not having graduation on time, so proper remediation and retention policies can be formulated and implemented by institutions. The student graduation rate is the percentage of a school’s first-time, first-year undergraduate students who complete their program successfully. Most students’ first-year freshmen enrolled at the tertiary level failed to graduate. According to the National Center for Education Statistics, almost half of the first time freshmen full-time students who began seeking a bachelor’s degree do not graduate. The colleges and universities consisting of high leaver rates go through a loss of fees and potential alumni contributors.


2016 ◽  
pp. 970-987
Author(s):  
Dheeraj Raju ◽  
Randall Schumacker

The goal of this research study was to compare data mining techniques in predicting student graduation. The data included demographics, high school, ACT profile, and college indicators from 1995-2005 for first-time, full-time freshman students with a six year graduation timeline for a flagship university in the south east United States. The results indicated no difference in misclassification rates between logistic regression, decision tree, neural network, and random forest models. The results from the study suggest that institutional researchers should build and compare different data mining models and choose the best one based on its advantages. The results can be used to predict students at risk and help these students graduate.


2016 ◽  
Vol 6 (2) ◽  
pp. 38-54 ◽  
Author(s):  
Dheeraj Raju ◽  
Randall Schumacker

The goal of this research study was to compare data mining techniques in predicting student graduation. The data included demographics, high school, ACT profile, and college indicators from 1995-2005 for first-time, full-time freshman students with a six year graduation timeline for a flagship university in the south east United States. The results indicated no difference in misclassification rates between logistic regression, decision tree, neural network, and random forest models. The results from the study suggest that institutional researchers should build and compare different data mining models and choose the best one based on its advantages. The results can be used to predict students at risk and help these students graduate.


Author(s):  
Ivan Obreshkov ◽  

The severe acute respiratory syndrome coronavirus SARS-CoV-2 pandemic brought changes in various aspects of life, including educational field. The present study reveals some of the challenges related to real-time distance learning for university students majoring in tourism in Plovdiv, Bulgaria. The study includes Bulgarian and international students in full-time and part-time bachelor's and master's tourism programs, in which real-time distance education was introduced for the first time. The current study could be a starting point for improving the organization and quality of education of Tourism students, as well as for faster overcoming of related difficulties in communication with students.


2006 ◽  
Vol 88 (10) ◽  
pp. 333-333
Author(s):  
Charlotte Worker

Until recently it has been difficult for general dental practitioners (GDPs) to access formally recognised postgraduate training while maintaining a full-time commitment to practice. The diploma in restorative dentistry from the Faculty of General Dental Practice (UK) (FGDP(UK)) allows participants to do just that. In the latest development GDPs now have the option, for the first time, to choose a special interest module in aesthetic dentistry during the second year of the part-time diploma programme.


Author(s):  
Sera J. Zegre ◽  
Rodney P. Hughes ◽  
Andrew M. Darling ◽  
Craig R. Decker

This study examines the relationship between campus recreation facility access and first-year retention of full-time, first-time undergraduate students at a public university for 2014–2015 through 2016–2017. Authors examine differences between facility users and nonusers by pairing facility swipe card data with student records. Statistical analysis includes logistic regression and matching approaches, controlling for student demographics, academic preparedness, academic goals, family characteristics, and various environmental factors. Results show a positive and significant relationship between recreation facility use and retention, including 7.1 to 8.4 percentage points higher retention for users versus nonusers, holding other variables constant. Subsample analysis suggests the relationship between recreation facility use and retention differs across student subgroups. Key study contributions include linking card swipe data on facility usage with extensive student records, clearly defining facility users and nonusers, and introducing a new robustness check based on assignment of students to residence halls different distances from recreation facilities.


2018 ◽  
Vol 88 (2) ◽  
pp. 227-244 ◽  
Author(s):  
CONSTANCE ILOH

The past two decades have seen massive changes in the higher education landscape, including the heightened participation of post-traditional students, high reentry and mobility of students within and across sectors, and the increased visibility of open admissions institutions, such as community colleges and for-profit colleges. Despite these radical shifts, the most commonly used college choice frameworks still focus on the decisions of students who fit a stereotypical profile and are entering traditional institutions of higher learning for the first time. In this article, Constance Iloh argues for the necessity of a new conceptual approach and offers a three-component ecological model of college-going decisions and trajectories that incorporates the pressing conditions and shifting contexts of twenty-first-century postsecondary education. In doing so, Iloh also asserts that the concept of “choice” may be a limited and problematic way of understanding present-day college-going. Errata The Editorial Board of the Harvard Educational Review is issuing an errata statement in conjunction with “Toward a New Model of College ‘Choice’ for a Twenty-First-Century Context” (Volume 88, Number 2, pages 227-244, doi:10.17763/1943-5045-88.2.227), by Constance Iloh, due to multiple instances in which the author incompletely attributed previously published material in the introduction and literature review. Given these extensive citation errors, the Editorial Board felt it important to correct the scholarly record. Pages 228-232 of the published article contain the following incompletely attributed materials: Excerpt lacking quotation marks from Heil, S., Reisel, L., & Attewell, P. (2014). College selectivity and degree completion. American Educational Research Journal, 51(5), 913-935. https://doi.org/10.3102/0002831214544298Excerpt lacking quotation marks from Cabrera, A. F., & La Nasa, S. M. (2002). Understanding the college-choice process. New Directions for Institutional Research, 2000(107), 5-22. https://onlinelibrary.wiley.com/doi/epdf/10.1002/ir.10701Two excerpts lacking quotation marks from Niu, S. X., Tienda, M., & Cortes, K. (2006). College selectivity and the Texas top 10% law. Economics of Education Review, 25(3), 259-272. doi:10.1016/j.econedurev.2005.02.006Excerpt lacking quotation marks from Cabrera, A. F., & La Nasa, S. M. (2000). Understanding the college-choice process. In A. F. Cabrera & S. M. La Nasa (Eds.), Understanding the college choice of disadvantaged students: New directions for institutional research. San Francisco: Jossey-Bass.Excerpt lacking quotation marks from Chen, J. C. (2017). Nontraditional adult learners. SAGE Open, 7(1). doi:10.1177/2158244017697161Quote lacking quotation marks and citation from Robert Hansen, CEO of University Professional and Continuing Education Association (UPCEA) as reported in Inside Track. (2015). National study of non-first-time students shows full-time enrollment may not be appropriate for all. Retrieved from https://www.insidetrack.com/national-study-of-non-first-time-students-shows-full-time-enrollment-may-not-be-appropriate-for-all/Excerpt lacking quotation marks and citation from Bidwell, A. (2014, July 29). 31 million in higher education limbo: Some college, no degree. US News & World Report. Retrieved from https://www.usnews.com/news/articles/2014/07/29/31-million-in-higher-education-limbo-some-college-no-degreeExcerpt lacking quotation marks from Tudge, J. R. H. (2008). The everyday lives of young children: Culture, class, and child rearing in diverse societies. New York: Cambridge University Press. doi:10.1017/ CBO9780511499890


1974 ◽  
Vol 21 (6) ◽  
pp. 503-504

Grants to teach abroad are available under the Fulbright-Hays Act for the 1975–76 academic year. Elementary and secondary teachers, college instructors, and assistant professors are eligible to participate in the program. United States citizenship, a bachelor's degree, and at least three years of successful full-time teaching are required for teaching positions. Application should be made before 1 November 1974. An information bulletin and application forms may be obtained from the Teacher Exchange Section, Division of International Education, U.S. Office of Education, Washington, D.C. 20202.


2014 ◽  
Vol 25 (2) ◽  
pp. 221-241 ◽  
Author(s):  
Edward Foster

Abstract This note rearranges the data from Census Bureau Personal Income (PINC) tables 32–35 showing earnings of full-time, year-round workers from 1974 to 2012 to display the 39-year time series for average real earnings by education, age group, and sex. Aggregated data show strong upward trends for all males and all females combined, for males and females with a bachelor's degree or more and for those with less than a bachelor's degree. However, all trends have flattened or become negative since 2000. Shifts in the composition of the work force over time mean that trends in aggregated earnings incorporate those shifts, so may not be useful for projecting earnings growth for any individual plaintiff of a specific age and educational background. The note addresses that problem in two ways: First it re-weights the aggregate statistics to remove some effects of shifts in composition of the workforce. Second it gives summary statistics for log-linear regressions of real earnings on time for all education-age-sex combinations for the period 1974–1999 and for 2000–2012. Growth for the latter period is negative for most of those combinations. Supplemental material for a Microsoft Excel workbook contains the underlying data and several figures and is accessible from the Journal of Forensic Economics website.


Author(s):  
Markéta Babičová ◽  
Ingrid Nagyová

Abstract The course Nursing Procedures and Interventions is being taught at the Faculty of Medicine of the University of Ostrava within the scope of the study programs Nursing and Midwifery. Despite the fact that the main part of the course is dedicated to the practical medical skills, it is suitable not only for students of full-time studies, but also for students of combined studies. The teaching of the course is organizationally demanding, because of which a Moodle e-learning course has been developed. The article describes the aims and the education process of the course Nursing Procedures and Interventions with the support of e-learning. It deals especially with the testing of theoretical knowledge of students within the e-learning course, which has three phases - when introduced to the course for the first time, during the course, and at the end of it. The article presents the comparison of the test results of different education periods. The article also deals with the more complicated issues and parts of the course and also compares students’ results with regard to their previous specialty - if they already encountered any kind of health studies or if the course is their first experience with this kind of education.


Sign in / Sign up

Export Citation Format

Share Document