Analyzing the Data Collected by Programming Tutors that Provide Post-Practice Reflection (original) (raw)

2007, Seventh IEEE International Conference on Advanced Learning Technologies (ICALT 2007)

We used megavariate analysis techniques to analyze the data collected by programming tutors in order to find the relationships, if any, between the correctness of a student's answer, and several independent variables including the number of steps in the correct answer, the time taken by the student to solve each problem, the number of problems solved by the student during the tutoring session, the hardness of the concept underlying each problem, and the number of attempts needed by the student to correctly identify the concept underlying each problem during postpractice reflection. After eliminating outliers determined through combined variance of all the independent variables, we found that correctly solving the problem is closely associated with the number of attempts needed by the learner to identify the underlying concept during post-practice reflection. Therefore, the reflection questions as presented by our tutors correctly assess understanding of the concept underlying each problem.

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact