Young, M. G., & Greco, E. C., & Jordan, S. M., & Limperis, T. G. (2019, June), Regression Analysis to Predict Student Electric Circuits Performance  Paper presented at 2019 ASEE Annual Conference & Exposition , Tampa, Florida. 10.18260/1-2--33231

\bibitem{asee_peer_33231}
  Young, M. G., \& Greco, E. C., \& Jordan, S. M., \& Limperis, T. G. (2019, June), \emph{Regression Analysis to Predict Student Electric Circuits Performance}
  Paper presented at 2019 ASEE Annual Conference \& Exposition , Tampa, Florida.
  10.18260/1-2--33231

Matthew Garett Young, Edward Carl Greco Jr., Scott Marks Jordan, and Thomas Galen Limperis.  "Regression Analysis to Predict Student Electric Circuits Performance".  2019 ASEE Annual Conference & Exposition , Tampa, Florida, 2019, June.  ASEE Conferences, 2019.  https://peer.asee.org/33231 Internet.  29 Jun, 2024

\bibitem{asee_peer_33231}
  Matthew Garett Young, Edward Carl Greco Jr., Scott Marks Jordan, and Thomas Galen Limperis.
  "Regression Analysis to Predict Student Electric Circuits Performance".
  \emph{2019 ASEE Annual Conference \& Exposition , Tampa, Florida, 2019, June}.
  ASEE Conferences, 2019.
  https://peer.asee.org/33231 Internet.  29 Jun, 2024

@INPROCEEDINGS{asee_peer_33231
author = "Matthew Garett Young, Edward Carl Greco Jr., Scott Marks Jordan, and Thomas Galen Limperis"
title = "Regression Analysis to Predict Student Electric Circuits Performance"
booktitle = "2019 ASEE Annual Conference \& Exposition "
year = "2019"
month = "June"
address = "Tampa, Florida"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/33231}
number = {10.18260/1-2--33231}
}

TY  - CPAPER
AB  - We have developed a proportional odds logistic regression (POLR) model in the R programming language that can provide supporting data to aid in engineering student retention.  The primary goal of the regression analysis is to identify populations of students who are at most risk of not succeeding (making lower than a grade of  ‘C’) in their undergraduate electrical engineering courses.   
Electric Circuits is a cornerstone course in many electrical engineering curriculums.  Pre-requisite course performance can be an indicator of future course performance for undergraduate students.  Following this logic, it would not be surprising to think that Calculus I and Calculus II might be strong predictors of Electric Circuits I performance.  However, the POLR we have employed shows that Calculus I and II are relatively weak predictors of Electric Circuits I performance whereas cumulative GPA seems to be the strongest predictor.  This might not be a surprise to those that have suggested that the overall content of Electric Circuits I consists mainly of algebra.  Nonetheless, one would think that a student who is proficient at algebra would also be skilled at Calculus I and II, and thus Electric Circuits I via the pre-requisite argument.  While our model does not discount that strong student performance in Calculus I and II also correlate to strong performance in Electric Circuits I, it does provide convincing evidence that cumulative GPA is the best metric to examine for predicting student success.
The present research is an expansion of research presented at the ASEE 2018 Midwest Regional conference.   Also, we have incorporated additional analysis techniques to determine how factors are correlated, thus potentially increasing the prediction capability of success in the model.  


AU  - Matthew Garett Young
AU  - Edward Carl Greco Jr.
AU  - Scott Marks Jordan
AU  - Thomas Galen Limperis
CY  - Tampa, Florida
DA  - 2019/06/15
PB  - ASEE Conferences
TI  - Regression Analysis to Predict Student Electric Circuits Performance
UR  - https://peer.asee.org/33231
DO  - 10.18260/1-2--33231
ER  -