TY - JOUR
T1 - An Empirical Analysis of the Impact of Continuous Assessment on the Final Exam Mark
AU - Morales, María
AU - Salmerón, Antonio
AU - Maldonado, Ana D.
AU - Masegosa, Andrés R.
AU - Rumí, Rafael
N1 - Funding Information:
This research is part of Project PID2019-106758GB-C32 funded by MCIN/AEI/10.13039/501100011033, FEDER “Una manera de hacer Europa” funds. This research is also partially funded by Junta de Andalucía grant P20-00091 and University of Almería grant UAL2020-FQM-B196.
Publisher Copyright:
© 2022 by the authors.
PY - 2022/11
Y1 - 2022/11
N2 - Since the Bologna Process was adopted, continuous assessment has been a cornerstone in the curriculum of most of the courses in the different degrees offered by the Spanish Universities. Continuous assessment plays an important role in both students’ and lecturers’ academic lives. In this study, we analyze the effect of the continuous assessment on the performance of the students in their final exams in courses of Statistics at the University of Almería. Specifically, we study if the performance of a student in the continuous assessment determines the score obtained in the final exam of the course in such a way that this score can be predicted in advance using the continuous assessment performance as an explanatory variable. After using and comparing some powerful statistical procedures, such as linear, quantile and logistic regression, artificial neural networks and Bayesian networks, we conclude that, while the fact that a student passes or fails the final exam can be properly predicted, a more detailed forecast about the grade obtained is not possible.
AB - Since the Bologna Process was adopted, continuous assessment has been a cornerstone in the curriculum of most of the courses in the different degrees offered by the Spanish Universities. Continuous assessment plays an important role in both students’ and lecturers’ academic lives. In this study, we analyze the effect of the continuous assessment on the performance of the students in their final exams in courses of Statistics at the University of Almería. Specifically, we study if the performance of a student in the continuous assessment determines the score obtained in the final exam of the course in such a way that this score can be predicted in advance using the continuous assessment performance as an explanatory variable. After using and comparing some powerful statistical procedures, such as linear, quantile and logistic regression, artificial neural networks and Bayesian networks, we conclude that, while the fact that a student passes or fails the final exam can be properly predicted, a more detailed forecast about the grade obtained is not possible.
KW - artificial neural networks
KW - Bayesian networks
KW - classification
KW - continuous assessment
UR - http://www.scopus.com/inward/record.url?scp=85141826498&partnerID=8YFLogxK
U2 - 10.3390/math10213994
DO - 10.3390/math10213994
M3 - Journal article
AN - SCOPUS:85141826498
SN - 2227-7390
VL - 10
JO - Mathematics
JF - Mathematics
IS - 21
M1 - 3994
ER -