Data on online and face-to-face course enrollments in a public research university during summer terms

This data article includes information on institutional data at a large public research university in Southern California. In particular, data on undergraduate student enrollments in online and face-to-face courses during summer terms from 2014 to 2017 cumulating in 72,441 course enrollments from 23,610 undergraduate students in 433 courses is provided. This data includes additional information on the statistical models examining factors influencing student enrollment by course modality and the associations of course modality with course grades. This includes descriptive data and data derived from multi-level logistic regression analyses and multi-way fixed effects linear regression analyses. This data article is associated with the article “Effects of course modality in summer session: Enrollment patterns and student performance in face-to-face and online classes” [1].


Data
This Data in Brief article is associated with the article "Effects of course modality in summer session: Enrollment patterns and student performance in face-to-face and online classes" [1]. The data provided in this article sheds light on the demographics at a large research university during summer terms (Tables 1e3, Table 8) and models associations of student-and course-level factors influencing course enrollments by course modality (Tables 4e7). In addition, the data describes associations of course modality with student course grades (Tables 9e19). Specifications Table   Subject area Education More specific subject area Higher Education, Online Learning Type of data Tables  How data was acquired Institutional data base of the University of California, Irvine Data format Analyzed, raw (upon request)

Experimental factors
Course enrollments and student grades by course modality Experimental features Logistic regression analysis, fixed effects modeling Data source location Irvine, CA, USA Data accessibility Data is within this article. Access to de-identified raw data is available upon request to the corresponding author for researchers with an approved IRB from their home institution.

Related research article
This article provides supplemental information for research published in the following study: Fischer, C., Xu, D., Rodriguez, F., Denaro, K., & Warschauer, M. (2020). Effects of course modality in summer session: Enrollment patterns and student performance in face-to-face and online classes, The Internet and Higher Education, 45, 1-9 Value of the Data Insights on undergraduate course enrollments during summer terms may guide further development of summer course portfolios.
Insights on similarities and differences in student enrollment in online and face-to-face courses may guide adaptation of online course portfolios. Details on the applied methodology and additional information on the applied statistical models may encourage replication studies and secondary data analyses.

Details of institutional data
Students enrolled in undergraduate courses at in the 2014 to 2017 summer terms were included in this data. This data includes enrollments from degree-seeking undergraduate students in lecture    The data consisted of student-level demographic, performance, and college career information, as well as course-level information. Student-level demographic information included gender (i.e., female, male), racial/ethnic background (i.e., White; Asian or Asian American; Black or African American; Latino or Hispanic; American Indian, Alaska Native, or Pacific Islander), first-generation college student status (i.e., neither parent holds a Bachelor's degree or higher), low-income status (i.e., derived from family household income  and household size using 185% of the U.S. poverty line), English language learner status (i.e., Language other than English is students' first language), and whether or not the student is a California resident. Student performance indicators include, standardized admission test score (i.e., measured through American College Testing (ACT) and the Scholastic Aptitude Test (SAT) scores) and current college grade point averages. College career characteristics included students' years of enrollment in the institution, transfer student status, the number of online courses taken in college, and whether students repeated courses.
Course-level data includes course grades, course code, department, year and term the course was offered, the number of students enrolled in a course, course modality (i.e., online or face-to-face course modality), and unique instructor identification information. Table 1 describes the overall data of all summer course enrollments prior to any list-wise deletion.

Data on multi-level logistic regression analysis
The following tables describe descriptive information of (a) all course enrollments, (b) all face-toface course enrollments, and (c) all online course enrollments. This information is provided for both   the full sample (all course enrollments) and a restricted sample that only includes courses that were offered as both online and face-to-face courses in the same term (Tables 2 and 3). These descriptive information are provided after listwise deletion. In addition, Tables 4e7 provide additional information on the two-level logistic regression models [2]. The models were conducted applying the meqrlogit syntax in Stata 15 [3]. In particular, course enrollments (level 1) were nested into courses (level 2).

Data on multi-way fixed effects modelling
The following table describes descriptive information for (a) all course enrollments, (b) all course enrollments of low-income students, (c) all course enrollments of first-generation college students, and (d) all course enrollments of students in the lower high school performance subgroup. This information is displayed separately by online and face-to-face course enrollments (Table 8). The descriptive information of time-variant variables is provided after listwise deletion (also accounting for missingness in the grouping variables (i.e., low-income status, first-generation college student status, high school performance indicator). In addition, Tables 9e19 provide additional information on the multi-way fixed effects linear regression models [4,5]. The models sequentially introduced student, course, year, and instructor fixed effects and were conducted applying the xtreg syntax in Stata 15 [6]. Please note that these tables do not display coefficients for the course, instructor, and year series of dummy variables.