The majority of the highest-paying, in-demand jobs now require specialized or general skills in data analysis, data processing and applied statistics (Glassdoor, 2019). While these and other technical occupations have been predicted to rise by 17.7 percent between 2012 and 2022 (U.S. Department of Labor, 2013), the relevance of data-oriented skills in many other growing careers and industries, previously less directly focused on analytics (e.g., health care and manufacturing) is also expanding (U.S. White House, 2014). These trends threaten to further increase social and economic disparities given the continued underrepresentation of both females and individuals from racially underrepresented groups across all positions within the technology industry (Mangalindan, 2014).
As one of the largest and most diverse majors nationwide to require training in data analysis and applied statistics, psychology courses serve as many of the most popular and promising opportunities for students to gain exposure to these transformational skills. Psychology instructors of all kinds, but particularly those who teach courses in statistics and research methods have great potential for breaking down long-standing disparities and contributing to opening the analytics economy to everyone. This potential is most often realized with exposure that is both early and often and that works double-time to inspire students to approach these skills as a vehicle for answering questions that they feel passionately about. It is more than just offering a seat in the classroom. Psychology as a discipline is particularly well-equipped to provide a warm, welcoming (and empowering), place at the table.
It is within this context that we have developed Passion-Driven Statistics as an innovative instructional model. Passion-Driven Statistics is a flexible, project-based, introductory curriculum that has been implemented as a statistics course, a research methods course, a data science course, a capstone experience, and a summer research boot camp with students from a wide variety of academic settings. Liberal arts colleges, large state universities, regional colleges/universities, medical schools, community colleges and high schools have all successfully implemented the model. Funded by the National Science Foundation, the curriculum engages students in authentic projects with large, real-world data sets (e.g. National Household Survey on Drug Use and Health, The Behavioral Risk Factor Surveillance System, and National Longitudinal Study of Adolescent to Adult Health) from the very first day! (Dierker et al., 2012). There are no canned exercises, and at the same time, no M&M’s or other entertaining maneuvers. Instead, the focus is on welcoming and empowering students to ask and answer questions they care about. Is exposure to a drug use prevention curriculum associated with lower rates of experimentation with diverse substances? Are religious adolescents less likely to be depressed? What factors predict “safe sex” practices? As students engage in productive struggle in the context of their own original research, the instructor and peer mentors support each student individually through ample one-on-one mentoring. Together, we take students completely out of their comfort zone, and at the same time “love them through it” by creating an inviting classroom culture and an experience that gives students a safe and supportive space to “get it wrong before they get it right,” no matter their educational background or experience.
The curriculum specifically teaches statistical thinking by asking students to choose their own research questions and giving them time to think critically about statistical issues related specifically to their project. Notably, our students learn to recognize the usefulness of data for answering questions of interest to them (and to society) and tackle complicated real-world questions that involve more than just one or two variables. Further, by supporting students to make their own decisions about the most appropriate ways to visualize, explore, analyze, and ultimately, present data, Passion-Driven Statistics provides an opportunity to become fluent in the work of quantitative research. The curriculum covers basic themes such as measurement and descriptive and graphical representation, as well as more specific inferential methods needed to test hypotheses and/or explore the empirical structure of data. What makes the approach unique is that all of these topics are introduced as students’ own research questions dictate. In this way, students are provided with opportunities to learn to select the tools that are most appropriate to address their research questions and to engage in statistical decision making. Using leading statistical software, including SAS, R, Stata, Python and SPSS, our students are exposed to a wide variety of statistical methods and learn to choose and use them flexibly as they are needed.
Research evaluating the modelopens in new window has been exciting to see unfold. The curriculum attracts higher rates of underrepresented minority (URM) students compared to a traditional statistics course, and students enrolled in Passion-Driven Statistics are more likely to report increased confidence in working with data and increased interest in pursuing advanced statistics coursework (Dierker et al., 2018). Given our emphasis on coding, we have also compared enrollments to those of introductory programming courses, showing that Passion-Driven Statistics enrolls higher rates of both women and URM students (Cooper & Dierker, 2017). In new research currently under review, the project-based curriculum promoted further training in statistics. Using causal inference techniques to achieve matched comparisons across three different statistics courses, students originally enrolled in Passion-Driven Statistics were significantly more likely to take at least one additional undergraduate course focused on statistical concepts, applied data analysis, and/or use of statistical software compared to students taking either an exercise-based psychology statistics course or traditional math statistics course. Further, Passion-Driven Statistics students took a larger number of one of these additional courses compared to students originally enrolled in either of the comparison courses.
A variety of resources for Passion-Driven Statisticsopens in new window are available online. Some that you might find most helpful include: (1) a free e-bookopens in new window, with links to videos that allow you to “flip” the classroom, and (2), translation codeopens in new window aimed at supporting the use of statistical software across all of the major platforms (i.e. SAS, R, python, Stata and SPSS). We are currently in the second year of a five-year NSF grant aimed at nationwide dissemination of the model. If you are interested in learning more or attending one of several faculty workshops, I would encourage you to contact me.
Early in my career, I imagined that someone in the academy from a higher pay grade or possessing a bigger job title than my own was going to come up with the solution to break down the pervasive and longstanding disparities. That was until I realized that it is in all of our hands. As professors of psychology, I believe that we may have more power on this front than most.
Lisa Dierker is the Walter Crowell University Professor of Social Sciences and professor of psychology at Wesleyan University. She received her PhD in developmental psychology from the University of Connecticut and completed postdoctoral training in epidemiology at the Yale School of Medicine. A researcher in addictive behaviors, her more recent work based on the NSF-funded Passion-Driven Statistics Project centers on the dissemination of innovative pedagogical practices.
References
Cooper, J., & Dierker, L. (2017). Increasing exposure to programming: A comparison of demographic characteristics of students enrolled in introductory computer science programming courses vs. a multidisciplinary data analysis course. International Research in Higher Education, 2(1), 92-100. DOI: 10.5430/irhe.v2n1p92
Dierker, L., Kaparakis, E., Rose, J. & Selya, A. (2012). Strength in numbers: A multidisciplinary, project-based course in introductory statistics. Journal of Effective Teaching, 12(2): 4-14.
Dierker, L., Woods, K., Singer-Freeman, K., Germano, K.,Cooper, J.L. & Rose, J. (2018). Evaluating Impact: A comparison of learning experiences and outcomes of students completing a traditional versus multidisciplinary, project-based introductory statistics course, International Journal of Education, Training and Learning, 2(1), 16-28.
Glassdoor (2019). 25 highest paying jobs in demand. [cited January 19, 2020]; https://www.glassdoor.com/List/Highest-Paying-Jobs-LST_KQ0,19.htmopens in new window
Mangalindan J. (2014). How tech companies compare in employee diversity. https://fortune.com/2014/08/29/how-tech-companies-compare-in-employee-diversity/opens in new window
U.S. Department of Labor, Bureau of Labor Statistics. Employment projections: Employment by dailed occupation. 2013 [cited September 18, 2019]; https://www.bls.gov/emp/ep_table_102.htmopens in new window.
U.S. White House (2014). Ready to Work: Job-Driven Training and American Opportunity. [cited; October 16, 2019], https://obamawhitehouse.archives.gov/sites/default/files/docs/skills_report.pdfopens in new window