Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Entire DC Network
Investigating The Factors That Best Describe Student Experience And Performance In College, Abigale Wynn
Investigating The Factors That Best Describe Student Experience And Performance In College, Abigale Wynn
Undergraduate Honors Thesis Collection
The National Survey of Student Engagement (NSSE) surveys students at four-year institutions around the United States in order to offer Universities accessible ways to evaluate their students' experiences and performance. The NSSE data is collected in the form of a Likert-scale survey geared towards first year and senior year students. It asks questions about how they spend their time throughout the academic year and how they rate their experience. This thesis looks at the NSSE survey data from Butler University in 2016 and attempts to apply classification techniques and predictive models to draw conclusions about student performance. Methods such as …
Utilizing Multi-Level Classification Techniques To Predict Adverse Drug Effects And Reactions, Victoria Puhl
Utilizing Multi-Level Classification Techniques To Predict Adverse Drug Effects And Reactions, Victoria Puhl
Undergraduate Honors Thesis Collection
Multi-class classification models are used to predict categorical response variables with more than two possible outcomes. A collection of multi-class classification techniques such as Multinomial Logistic Regression, Na\"{i}ve Bayes, and Support Vector Machine is used in predicting patients’ drug reactions and adverse drug effects based on patients’ demographic and drug administration. The newly released 2018 data on drug reactions and adverse drug effects from U.S. Food and Drug Administration are tested with the models. The applicability of model evaluation measures such as sensitivity, specificity and prediction accuracy in multi-class settings, are also discussed.