1. ABOUT THE DATASET -------------------- Title: Dataset for "Online Formative Assessments Improve Student Performance in Large-Cohort Engineering Education" Creator(s): Qingen Meng Organisation(s): University of Leeds Rights-holder(s): Copyright 2023 University of Leeds Publication Year: 2026 Description: This dataset contains the underlying data supporting the findings reported in the paper Online Formative Assessments Improve Student Performance in Large-Cohort Engineering Education. Cite as: Meng (2026): Dataset for "Online Formative Assessments Improve Student Performance in Large-Cohort Engineering Education". University of Leeds. [Dataset] https://doi.org/10.5518/1930. Related publication: Meng Qingen (2026). Online Formative Assessments Improve Student Performance in Large-Cohort Engineering Education, Submitted. Contact: Q.Meng@leeds.ac.uk 2. TERMS OF USE --------------- Copyright 2026 University of Leeds, under a CC-BY-NC license. 3. PROJECT AND FUNDING INFORMATION ---------------------------------- Title: On the formative assessment and feedback for a substantial student cohort Dates: June 2024 - September 2025 Funding organisation: NA Grant no.: This dataset was not created in the course of a funded project. 4. CONTENTS ----------- File listing Assessment Marks.xlsx：This dataset contains the raw data underlying the study, including results from three assessments and three engagement categories for each assessment. The file comprises three worksheets, each containing the marks for one assessment, with students categorised into three levels of engagement (low, medium, and high). Data for Figures.xlsx: This file contains the statistical data used to generate Figures 1-3. Figure 1 was generated from Assessment 1 results, Figure 2 from Assessment 2 results, and Figure 3 from Assessment 3 results. The data include the mean scores and standard deviations for the low-, medium-, and high-engagement groups used in the graphical presentation of the results. 5. METHODS ---------- The aim of this study was to investigate the effectiveness of online formative assessments (OFAs). To achieve this, OFAs were developed for eight units of Semester 2 content of and Engineering Mechanics module at the University of Leeds through the University's virtual learning environment (Minerva). Students’ engagement data with the self-test questions were automatically recorded by the system in compliance with the Student Privacy Notice and Code of Practice for Learning Analytics. Student engagement with the OFAs was measured by the number of units for which formative assessments were attempted. Students were classified into three engagement groups: high engagement (more than five units attempted), medium engagement (one to four units attempted), and low engagement (no attempts). After the final exam, the effectiveness of the OFAs was evaluated by comparing the performance of the three engagement groups across: (1) Engineering Mechanics final examination questions aligned with the OFA content (Assessment 1), (2) Engineering Mechanics final examination questions not directly related to the OFAs (Assessment 2), and (3) performance in a separate module (Assessment 3). Data collection was in compliance with the Student Privacy Notice and Code of Practice for Learning Analytics. Mean scores and standard deviations were calculated for each engagement group, and one-way ANOVA tests were used to determine whether differences in performance between engagement levels were statistically significant. More details can be found here: Meng Qingen (2026). Online Formative Assessments Improve Student Performance in Large-Cohort Engineering Education, Cogent Education, Submitted.