Predicting the Enrollments in Humanities and STEM Programs in Higher Education Using ARIMAX Models

Predicting the Enrollments in Humanities and STEM Programs in Higher Education Using ARIMAX Models

Dian-Fu Chang, Wen-Shan Zhu, Shu-Jing Wu
Copyright: © 2022 |Pages: 15
DOI: 10.4018/IJOPCD.311435
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Traditionally, the participation patterns in the humanities and STEM (science, technology, engineering, and mathematics) programs in higher education differ. This study aimed to tackle this issue using concurrent time series data sets in the expanding higher education system. Authors selected the higher education system in Taiwan as an example. The participation in the humanities and STEM programs, covering 71 periods from 1950-2020, were collected from the Ministry of Education in Taiwan. The authors applied CCF (cross-correlation function) and ARIMAX (multivariable autoregressive integrated moving average) models to select the fittest model to predict the future trend. The humanities was the input variable and STEM was the output variable in the model. The findings revealed that ARIMAX (1,2,1) works well for these target data sets. According to the findings, enrollment in STEM programs will decrease with the decline in humanities programs in the future. This finding may provide useful information for related policy makers.
Article Preview
Top

Introduction

Enrollment in higher education has experienced explosive growth across Asia and other areas over the last decades. According to data from the UNESCO Institute for Statistics in 2018, the gross entrance ratio (GER) in high income countries moved to a universal stage (over 50%) in 1993. Some countries reached 75% in 2011, while the GER in most of the middle-income countries moved to the mass stage in 2001 (UNESCO Institute for Statistics, 2018). Higher education in Taiwan has expanded dramatically in the previous 3 decades. An overview of higher education in the past few decades revealed that the number of students increased from 299,486 (1976) to 576,623 (1999), and the GER rose from 15% to 50% within 23 years (Chang, 2017). The popularization of education has led to a rapid increase in student enrollment, although the figure has leveled off in the last decade. According to the 2015 Education Statistical Indicators, the tertiary education GER hit 83.88% in 2013, which was higher than that in most other Asian countries (Chang, 2017; MOE, 2016). Meanwhile, affected by the decline in the number of high school graduates, the enrollment in higher education decreased significantly in 2016, as 203 departments in 23 universities provided 2,953 vacant seats in 2016 (Taiwan People News, 2016). In other words, six universities could not attract 50% of their required enrollment. In 2017, the Ministry of Education announced at least 20 institutes in its university closing plan. Moreover, 123 departments were expected to close in 2019 (including graduate programs) (MOE, 2018). This could be an extreme example of the post-expansion phenomenon in global higher education systems. Within the system, the crisis caused by the expansion has still not been solved properly with sufficient research.

This article discusses higher education expansion as it has been directly addressed in existing enrollment in specific humanities and STEM programs. Will the enrollments in these two different programs impact each other? What kind of relationships are there between the humanities and STEM series? To tackle this phenomenon, the authors applied a multivariable autoregressive integrated moving average (ARIMAX) model to explore the time series data concurrently (Shumway & Stoffer, 2017). Taking Taiwan’s higher education enrollment as an example, the data for this study were collected from the Ministry of Education. Authors selected humanities and STEM programs in Taiwan as the research target to detect how the series data work within the expanding system. Given this purpose, this study explores the following research questions:

  • a How can the relationships between the two series be detected in the over-expanding higher education?

  • b Which ARIMAX model can work well to interpret the series concurrently?

  • c What kind of future trends can be interpreted with the fitted predicted model?

To answer these questions, this paper begins with the method section which presents the research framework, definition of target series data and the ARIMAX statistical process. The authors then present the related findings in the results section. Finally, the conclusion will be drawn.

Complete Article List

Search this Journal:
Reset
Volume 14: 1 Issue (2024)
Volume 13: 1 Issue (2023)
Volume 12: 4 Issues (2022)
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing