Predicting the pass probability of secondary school students taking online classes

https://doi.org/10.1016/j.compedu.2020.104110Get rights and content

Highlights

  • •

    Statistical analysis on multi-level factors with secondary online school big data.

  • •

    Finding 9 key factors highly associated with student pass in their online classes.

  • •

    Constructing a statistical model predicting the pass probability of online classes.

  • •

    Student background, learning activity, and course design affect the learning outcome.

Abstract

Empirical evidence on factors behind student success in secondary school online classes has been mixed and insufficient in its scope as well as data coverage. With a nationwide secondary school online class dataset with 26,345 students, this study attempts to identify factors of student success and first constructs a statistical model predicting the pass probability of online classes. The following student background variables are associated with a high pass rate: transfer students, graduation-year students, pass-experienced students, and students not re-registering for the course. With respect to learning activities, students who actively communicate with teachers/coordinators via messenger services or questions and answer sessions, or students who log in to the online class at the early stage of the semester are more likely to pass a course. Individual course characteristics are also found to be important for pass in courses requiring a summative exam, while courses for either subjects that have a good track record of students passing or courses for subjects that are taught by teachers with a good track record of students passing are correlated with a high pass rate. Logistic regression results suggest that the pass probability (odds ratio) is greatly increased when students have passing experience, actively interact with teachers/coordinators, or when the subject has a good student passing record.

Section snippets

Credit author statement

Hyeseung Maria Chang: Conceptualization, Writing – original draft, Writing - reviewing & editing, Validation, Formal analysis, Investigation. Visualization, Resources. Hyunjung Joseph Kim: Methodology, Formal analysis, Software, Writing – original draft, Data curation

Literature Review

To find out the main factors responsible for student success in online classes, this study defines a student's success as whether he/she attains a ‘pass’ for the online course. The online courses operated in Korea from 2012 recognize students' learning achievement as ‘pass’ or ‘fail’. A ‘pass’ is determined by several elements such as completing the minimum required amount of video-on-demand content, quizzes, formative evaluations, and a summative test. It is notable that the factors

Methods

As mentioned in the research questions, this paper finally aims to develop a model to predict the pass probability of secondary school students taking online classes. The prediction model will have students’ learning outcomes as a dependent variable along with associating explanatory variables. In this section, we introduce the data source for our empirical study, describe the variables, and explain the prediction model itself.

Student background

Table 4 shows the pass rate comparison between two groups divided by dummy variables, which are student background variables. For each dummy independent variable, one group has a higher pass rate in the online course than the other group. The last column of the table represents the pass rate differences between two groups with statistical significances, which are assessed by the chi-square test.

High school: The school level is not an explanatory variable in course completion. The pass rate is

Conclusions

This study contributes to existing research by providing empirical and comprehensive results in identifying explanatory variables associated with the probability of passing online courses at the secondary education level, which has not been sufficiently studied thus far. Using three-year datasets for online classes in Korea comprising 26,345 observations, this research explores explanatory variables and the prediction model of the probability of student pass in online secondary school classes.

Funding

This research did not receive any grant from funding agencies in the public, commercial or not-for-profit sectors.

Acknowledgements

We would like to express our appreciation and thanks to the participants of the ‘2018 Korea Educational Technology Conference’ for their insightful comments during and following the event. We also wish to thank to our colleagues, Mieun Jang and Sungeun Lee, for data cleaning and their wonderful research assistance. Our gratitude also goes to countless others– all of whom have encouraged and supported us during this study.

References (29)

  • T. Amemiya

    Advanced econometrics

    (1985)
  • R. Bernard et al.

    Antecedents to dropout in distance education: Does one model fit all?

    The Journal of Distance Education

    (1989)
  • D.R. Cox

    The regression analysis of binary sequences

    Journal of the Royal Statistical Society: Series B

    (1958)
  • R.G. Croninger et al.

    Teacher qualifications and early learning: Effects of certification, degree, and experience on first-grade student achievement

    Economics of Education Review

    (2007)
  • R. Croxton

    The role of interactivity in student satisfaction and persistence in online learning

    MERLOT Journal of Online Learning and Teaching

    (2014)
  • N. Dowd

    Technical college instructors' perceptions of the impact of online readiness and of student support services on student success in online courses

    (2012)
  • R. Fulbright

    A quantitative study investigating the effect of motivational text messages in online learning

    (2012)
  • R. Haley

    Evaluating the effectiveness of online learning at the high school level

    (2013)
  • E. Heyman

    Overcoming student retention issues in higher education online programs

    Online Journal of Distance Learning Administration

    (2010)
  • D.W. Hosmer et al.

    Goodness of fit tests for the multiple logistic regression model

    Communications in Statistics-Theory and Methods

    (1980)
  • J. Hung et al.

    Integrating data mining in program evaluation of K–12 online education

    Educational Technology & Society

    (2012)
  • K. Jordan

    Massive open online course completion rates revisited: Assessment, length and attrition

    International Review of Research in Open and Distance Learning

    (2015)
  • M.S. Kemp

    Student and teacher predictors on credit recovery program outcomes: A national analysis

    (2011)

  • 2019 final report of Online Classes

    (2020)

    • Cited by (7)

    View all citing articles on Scopus
    View full text
    © 2020 Elsevier Ltd. All rights reserved.