As part of the 2018 HPCC Systems Summit Community Day event:
Up first, Shah Muhummad Hamdi, Georgia State University, briefly discusses his poster, Dimensionality Reduction on Pbblas.
Following, Itauma Itauma presents his breakout session in the Machine Learning track.
In this study, multiple regression analysis is used to determine if high school students’ perception of their science self-efficacy, identity, and utility predict consideration to enroll in a college stem major. The HPCC Systems ML library will be used to build a multiple regression model utilizing secondary data analysis of the United States High School Longitudinal Study of 2009 (HSLS:09) dataset. The HSLS:09 is a national cohort study of over 23,000 ninth graders from 944 schools in 2009 through their secondary and post-secondary years including choices of college majors and careers. This study demonstrates the use of the HPCC Systems ML library for statistical modeling in education.
Itauma Itauma is a doctoral candidate at Keiser University, a computer science instructor at Wayne State University and an online instructor at Southern New Hampshire University. His interests lie in learning analytics and utilizing HPCC Systems for educational research. He has an undergraduate degree in Electrical Engineering from the University of Ilorin and two Masters Degrees, a Master of Science in Computer Engineering from Istanbul Technical University, majoring in human-robot interaction and a Master of Science in Computer Science from Wayne State University where his thesis was based on leveraging HPCC Systems for Big Data analytics.
4. Personal Information
Itauma Itauma
PhD Candidate,
Keiser University
@amightyo
Itauma Itauma is a doctoral candidate at Keiser University and a computer
science and data analytics instructor at Southern New Hampshire University.
His interests lie in education analytics, data visualization, and utilizing HPCC
Systems, SPSS, and R for educational research. He has an undergraduate
degree in Electrical Engineering from the University of Ilorin in Nigeria and two
Masters Degrees, a Master of Science in Computer Engineering from Istanbul
Technical University in Turkey, majoring in human-robot interaction and a
Master of Science in Computer Science from Wayne State University in US
where his thesis was based on leveraging HPCC Systems for Big Data
analytics.
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
7. Introduction
• STEM: Science, Technology,
Engineering, and Mathematics
• Critical thinking and problem solving
skills
• Increasing demand for STEM expertise
• Employment growth
• STEM 10.5% vs non-STEM
5.2% from 2009 - 2015 (Fayer,
Lacey, & Watson, 2017)
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
8. Background
Supply of STEM
workers needs to
keep up with demand
High schools
important in the
development of
STEM skills
• STEM pipeline
Intent to major in
STEM affected by
experiences in high
school
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
Self-efficacy, identity, and utility
have been associated with
motivation, selection of, and
persistence in career choices
9. Definition of Terms
Predicting College STEM Enrollment using HPCC Systems in Educational Research
Science Self-efficacy
• Confidence about ability to
succeed in science
Science Identity
• Seeing oneself as part of a
science community
Science Utility
• Perception of the utility of science
in everyday life and for the future.
10. Objective
• To determine if high school students’
perception of their science self-
efficacy, identity, and utility are
associated with consideration to
enroll in a college STEM major.
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
Objective
Self-
efficacy
Identity
Utility
11. Methods
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
• High School Longitudinal Study
(HSLS:09)
• Dataset of over 23,000 ninth graders
from 944 schools in 2009
• Bivariate analysis
Science self-
efficacy
Science identity
Science utility
Intent to Enroll in a STEM
Program
12. Correlation Matrix – Intent to Enroll in STEM
Predicting College STEM Enrollment using HPCC Systems
in Educational Research
Science Self-
Efficacy
Science Identity Science Utility
Science Self-
Efficacy
1.0000
Science Identity 0.5051 1.000
Science Utility 0.3548 0.4449 1.000
16. HPCC Systems in Educational Research
• Why HPCC Systems?
• Machine learning vs Statistical learning
• HPCC Systems advantage in
educational research
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
17. Data Visualization in HPCC Systems
• Pie Charts, Line graphs, Maps, and other
visual graphs
• Simplifies the complex
• Advanced features
• Integration of Tableau in HPCC Systems
Predicting College STEM Enrollment using HPCC Systems in
Educational Research
18. Integration of Tableau in
HPCC Systems
Predicting College STEM Enrollment using HPCC Systems in Educational Research
19. Conclusion
• Positive correlations regarding consideration to enroll in
STEM
• Science self-efficacy and identity
• Science self-efficacy and utility
• Science identity and utility
• Results show interesting clusters that educators need to
further investigate
Predicting College STEM Enrollment using HPCC Systems in
Educational Research