Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis
The portability of predictive models of academic performance has been widely studied in the field of learning platforms, but there are few studies in which the results of previous evaluations are used as factors. The aim of this work was to analyze portability precisely in this context, where preced...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/9/8/870 |
id |
doaj-6653349a9fa249b38489852dcaece375 |
---|---|
record_format |
Article |
spelling |
doaj-6653349a9fa249b38489852dcaece3752021-04-15T23:01:59ZengMDPI AGMathematics2227-73902021-04-01987087010.3390/math9080870Portability of Predictive Academic Performance Models: An Empirical Sensitivity AnalysisJose Luis Arroyo-Barrigüete0Susana Carabias-López1Tomas Curto-González2Adolfo Hernández3Department of Quantitative Methods, Pontifical University of Comillas, 28015 Madrid, SpainDepartment of Quantitative Methods, Pontifical University of Comillas, 28015 Madrid, SpainDepartment of Quantitative Methods, Pontifical University of Comillas, 28015 Madrid, SpainDepartment of Financial and Actuarial Economics and Statistics, Faculty of Commerce and Tourism, Complutense University of Madrid, 28040 Madrid, SpainThe portability of predictive models of academic performance has been widely studied in the field of learning platforms, but there are few studies in which the results of previous evaluations are used as factors. The aim of this work was to analyze portability precisely in this context, where preceding performance is used as a key predictor. Through a study designed to control the main confounding factors, the results of 170 students evaluated over two academic years were analyzed, developing various predictive models for a base group (BG) of 39 students. After the four best models were selected, they were validated using different statistical techniques. Finally, these models were applied to the remaining groups, controlling the number of different factors with respect to the BG. The results show that the models’ performance varies consistently with what was expected: as they move away from the BG (fewer common characteristics), the specificity of the four models tends to decrease.https://www.mdpi.com/2227-7390/9/8/870mathematics educationuniversity teachingacademic successquantitative researchpredictive modelsportability |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jose Luis Arroyo-Barrigüete Susana Carabias-López Tomas Curto-González Adolfo Hernández |
spellingShingle |
Jose Luis Arroyo-Barrigüete Susana Carabias-López Tomas Curto-González Adolfo Hernández Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis Mathematics mathematics education university teaching academic success quantitative research predictive models portability |
author_facet |
Jose Luis Arroyo-Barrigüete Susana Carabias-López Tomas Curto-González Adolfo Hernández |
author_sort |
Jose Luis Arroyo-Barrigüete |
title |
Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis |
title_short |
Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis |
title_full |
Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis |
title_fullStr |
Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis |
title_full_unstemmed |
Portability of Predictive Academic Performance Models: An Empirical Sensitivity Analysis |
title_sort |
portability of predictive academic performance models: an empirical sensitivity analysis |
publisher |
MDPI AG |
series |
Mathematics |
issn |
2227-7390 |
publishDate |
2021-04-01 |
description |
The portability of predictive models of academic performance has been widely studied in the field of learning platforms, but there are few studies in which the results of previous evaluations are used as factors. The aim of this work was to analyze portability precisely in this context, where preceding performance is used as a key predictor. Through a study designed to control the main confounding factors, the results of 170 students evaluated over two academic years were analyzed, developing various predictive models for a base group (BG) of 39 students. After the four best models were selected, they were validated using different statistical techniques. Finally, these models were applied to the remaining groups, controlling the number of different factors with respect to the BG. The results show that the models’ performance varies consistently with what was expected: as they move away from the BG (fewer common characteristics), the specificity of the four models tends to decrease. |
topic |
mathematics education university teaching academic success quantitative research predictive models portability |
url |
https://www.mdpi.com/2227-7390/9/8/870 |
work_keys_str_mv |
AT joseluisarroyobarriguete portabilityofpredictiveacademicperformancemodelsanempiricalsensitivityanalysis AT susanacarabiaslopez portabilityofpredictiveacademicperformancemodelsanempiricalsensitivityanalysis AT tomascurtogonzalez portabilityofpredictiveacademicperformancemodelsanempiricalsensitivityanalysis AT adolfohernandez portabilityofpredictiveacademicperformancemodelsanempiricalsensitivityanalysis |
_version_ |
1721525989437079552 |