Using random forest analysis to identify student demographic and high school‐level factors that predict college engineering major choice

Abstract

Background Given the importance of engineers to a nation's economy and potential innovation, it is imperative to encourage more students to consider engineering as a college major. Previous studies have identified a broad range of high school experiences and demographic factors associated with engineering major choice; however, these factors have rarely been ranked or ordered by relative importance. Purpose/Hypothesis This study leveraged comprehensive, longitudinal data to identify which high school‐level factors, including high school characteristics and student high school experiences as well as student demographic characteristics and background, rank as most important in terms of predictive power of engineering major choice. Design/Method Using data from a nationally representative survey, the High School Longitudinal Study of 2009, and the random forest method, a genre of machine learning, the most important high school‐level factors in terms of predictive power of engineering major choice were ranked. Results Random forest results indicate that student gender is the most important variable predicting engineering major choice, followed by high school math achievement and student beliefs and interests in math and science during high school. Conclusions Gender differences in engineering major choice suggest wider ranging cultural phenomena that need further investigation and systemic interventions. Research findings also highlight two other areas for potential interventions to promote engineering major choice: high school math achievement and beliefs and interests in math and science. Focusing interventions in these areas may lead to an increase in the number of students pursuing engineering.

Choosing an engineering major: A conceptual model of student pathways into engineering

“…Importantly, this perspective facilitates the understanding of how factors related to individual backgrounds, social networks, institutional academic programs, organizations, and the environment intersect in important ways to generate trends in engineering major participation. Using the life course perspective enables us to comprehensively illustrate how factors across different life stages are associated with engineering major choice, in line with other research showing the interconnectedness between K-12 and postsecondary education in helping encourage greater and more diverse participation in engineering (e.g., Tan et al, 2021).…”

“…Previous studies have identified a wide range of factors that are associated with student major choice. In general, these factors can be organized into three main categories: individual characteristics and factors, social influences, and structural factors (e.g., Adelman, 1998;Blickenstaff, 2005;Cruz & Kellam, 2018;Darolia et al, 2020;Griffith & Main, 2021;Johnson & Sheppard, 2004;Lent et al, 2008;Main et al, 2015;Main, Darolia, et al, 2017;Main & Ost, 2011, 2014Main, Tan, et al, 2020;Main, Xu, et al, 2017;Marra et al, 2012;Matusovich et al, 2010;Ong et al, 2011;Seymour & Hewitt, 1997;Tan et al, 2021;Tonso, 1999Tonso, , 2006Tsui, 2010). Individual characteristics can include student demographic characteristics, academic achievement, motivation, and identity, whereas structural factors can include high school characteristics, high school geographical location, and the availability of math and science courses.…”

“…Using structural equation modeling to analyze data from 6772 first-year college engineering students, Godwin et al (2016) found that in addition to gender, math and physics identities predict engineering career choice. Examining data from the high school longitudinal survey, Tan et al (2021) showed that students who select engineering majors differ by high school academic achievement (9th and 11th grade math achievement, grade point average [GPA], scholastic aptitude test [SAT] math scores), student interest in high school math, and math identity during high school. Main et al (2015) also showed that academic achievement in the first year of college, such as GPA, SAT scores, and grades earned in math and science courses as well as expected grades in the intended major, predicts engineering major choice and/or major switching behavior.…”

“…In addition to individual student academic achievement and demographic characteristics, structural factors such as those associated with high schools (e.g., enrollment size, geographical distance from postsecondary institutions, math and science course availability, and engineering-inspired curriculum) matter (e.g., Brophy et al, 2008;Darolia et al, 2018;Godwin et al, 2016Godwin et al, , 2017Lundy-Wagner et al, 2014;Main et al, 2018;Main, Darolia, et al, 2017;Martin et al, 2013;Tan et al, 2021). For example, Knight et al (2020) found that students who go on to engineering programs are more likely to graduate from high schools with higher proportions of college-going students than students who do not.…”

“…While some students select an engineering major to matriculate into upon college entry, for other students, engineering major choice is a two-step process: (1) selecting to matriculate into a first-year or general engineering program and then (2) selecting into a specific engineering major such as chemical, civil, electrical, industrial, or mechanical engineering. However, studies on engineering major choice tend to focus on the choice of engineering as an aggregated field (e.g., Cruz & Kellam, 2018;Matusovich et al, 2010;Tan et al, 2021). Thus, they do not reveal the potential impact of major-specific subcultures, which may contribute to differences in levels of student diversity and academic outcomes (e.g., Bullard et al, 2010;Godfrey, 2007Godfrey, , 2014Lattuca et al, 2009;O'Connor et al, 2015;Trytten et al, 2004;Tsai et al, 2014).…”