Titus Winters

What do students know?: an outcomes-based assessment system

Well-run organizations collect, archive and analyze data relating to the effectiveness of their important processes. Educational institutions discard a wealth of student scores that could be analyzed. Each score contains important information about the student as well as the item (i.e., problem or question). This paper describes our project to develop an outcomes-based assessment system that mines per-item scores to track each students skills and knowledge. Statistical inference techniques from both educational statistics and data mining will quantitatively determine each students acquired competency, with minimal input from faculty. The culmination of item-level assessment gives individual faculty feedback on their courses, and gives curriculum committees feedback on which objectives are sufficiently met by their respective curricula.

Computer aided assessment with human oversight

For nearly fifty years, Computer Aided Assessment (CAA) in Computer Science has focused on the automated grading of programming assignments. Agar is a CAA framework that allows for automated grading of assignments, as well as efficient and effective human grading of subjective matters such as writing and code style. Agar features a system for reusable comments, which allows standard feedback and penalties to be assigned for a given error. The first time a given error is encountered, the grader writes out the comment and assigns it a penalty, and can simply select the comment and penalty from a list when the error is seen again. This approach reduces the amount of time require to grade, improves the uniformity of grading, and improves the quality of feedback to the students.to give quality feedback.