Rawson, K., & Stahovich, T. (2013, June), Predicting Course Performance from Homework Habits  Paper presented at 2013 ASEE Annual Conference & Exposition, Atlanta, Georgia. 10.18260/1-2--22359

\bibitem{asee_peer_22359}
  Rawson, K., \& Stahovich, T. (2013, June), \emph{Predicting Course Performance from Homework Habits}
  Paper presented at 2013 ASEE Annual Conference \& Exposition, Atlanta, Georgia.
  10.18260/1-2--22359

Kevin Rawson and Tom Stahovich.  "Predicting Course Performance from Homework Habits".  2013 ASEE Annual Conference & Exposition, Atlanta, Georgia, 2013, June.  ASEE Conferences, 2013.  https://peer.asee.org/22359 Internet.  10 Jul, 2024

\bibitem{asee_peer_22359}
  Kevin Rawson and Tom Stahovich.
  "Predicting Course Performance from Homework Habits".
  \emph{2013 ASEE Annual Conference \& Exposition, Atlanta, Georgia, 2013, June}.
  ASEE Conferences, 2013.
  https://peer.asee.org/22359 Internet.  10 Jul, 2024

@INPROCEEDINGS{asee_peer_22359
author = "Kevin Rawson and Tom Stahovich"
title = "Predicting Course Performance from Homework Habits"
booktitle = "2013 ASEE Annual Conference \& Exposition"
year = "2013"
month = "June"
address = "Atlanta, Georgia"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/22359}
number = {10.18260/1-2--22359}
}

TY  - CPAPER
AB  -              Predicting Course Performance from Homework HabitsHomework exercises are a cornerstone of modern instruction, especially in engineering. In thiswork, we seek to understand how student homework habits correlate with course performance.We conducted a study in which students in an undergraduate statics course used LivescribeTMsmartpens to complete all of their coursework, including homework, quizzes, and exams. Thesesmartpens serve the same purpose as traditional ink pens but additionally digitize thehandwriting, producing a digital, time-stamped record of the students' work. From this record,we can compute a variety of quantitative features characterizing the student’s homework habits.For example, for each assignment, we can compute the total amount of ink written, the totalamount of time spent completing the problems, the total amount of break time taken, the time ofthe day the student is working, and so on.We use regression models to examine how these features correlate with overall courseperformance, i.e., the final course grade. When constructing these models, we control for studentability using the students’ scores on the Force Concept Inventory (FCI), which is completedduring the first week of class. The FCI itself has some predictive ability; The FCI scorecorrelated with final course grade with R2 = 0.27. However, combining this score with the totalink written on the third homework assignment, which is the first assignment to includeequilibrium problems, produced a much stronger correlation with R2 = 0.35. A regression modelincluding the FCI score and four features computed from this assignment resulted in R2 = 0.43.Thus, by the end of the third week of a ten week course, it is possible to explain a significantamount of the variance in final course grade by considering homework habits.These results provide important insights about successful and unsuccessful homework habits.This work also provides a foundation for building early warning systems that examinehomework activity to identify students at risk of performing poorly in a course.
AU  - Kevin Rawson
AU  - Tom Stahovich
CY  - Atlanta, Georgia
DA  - 2013/06/23
PB  - ASEE Conferences
TI  - Predicting Course Performance from Homework Habits
UR  - https://peer.asee.org/22359
DO  - 10.18260/1-2--22359
ER  -