Question-Score Identity Detection (Q-SID)
Version 2.3 (July 2024)
Q-SID identifies groups of students whose question scores on exams are more similar to each other than is usual. Using this information, the course instructor can then compare the written answers of students within each group to determine if this similarity is due to collusion.
Educational instructors upload an excel file that contains the scores to each question for each student who took the exam as well as each students' total score. Q-SID
- gives each student a Collusion Score that defines the similarity of their exam to that of the partner in the class with the largest number of question scores identical to the student's,
- clusters any student/partner pairs that share unusually high Collusion Scores into small Collusion Groups of typically two to five students.
- assigns each Collusion Group an Empirical false positive rate (FPR) based on the frequency that Collusion Groups are found in strictly proctored examinations and, in many instances, a Synthetic FPR calculated from in silico data that mimics the distribution of question scores expected in the instructor's exam if no collusion occurred.
To use Q-SID, read the Q-SID Guide and go to the Analyze Data page. Students should read the explanation on the For Students page.
Q-SID was developed by researchers in the Department of Statistics at UCLA and at Lawrence Berkeley National Laboratory using exam data and instructor feedback from UC Berkeley and UCLA. Q-SID controls the FPR. Collusion Groups have Empirical FPRs of 0.04%, 0.20%, or 0.56% and Synthetic FPRs no higher than 0.8%, see the Q-SID Guide.
Q-SID works well for class sizes of 25 or more. It can identify up to 80% of the students who have colluded on a given exam, depending on the number of question scores provided. It requires at least 20 question scores and performs best with at least 50 scores. Q-SID can combine data from two or more exams from the same class to facilitate optimum analysis, see the Q-SID Guide. A detailed description of the Q-SID algorithm is available in this arXiv preprint.
Q-SID's goals are fourfold: One, to identify those students most likely to have colluded; Two, to protect the majority of students who obey their school's honor code by ensuring that they receive the grade that they deserve, not a lower one; Three, to deter cheating by informing students in advance that their exams will be screed by Q-SID; Four, to allow departments and institutions to measure collusion system-wide and thereby establish more informed policies. For discussion of the importance of using quantitative methods such as Q-SID to address collusion, read this Forbes article and listen to this podcast.
Q-SID does not store users' data or require registration. Nor does it record IP address, location or other user information. The Q-SID team would, however, welcome feedback on its performance. Feel free to email us about your experience with Q-SID at qsid@stat.ucla.edu.
Teachers employed by nonprofit institutions, as well as academic or nonprofit researchers, are permitted to use the Q-SID Program posted on this site subject to the Academic License.