Zanana, Avram (2025) A Comparison of Frequentist and Bayesian Approaches to Variable Selection in Logistic Regression for Heart Disease. Bachelor's Thesis, Mathematics.
|
Text
BachelorThesis.pdf Download (2MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
Toestemming.pdf Restricted to Registered users only Download (181kB) |
Abstract
Variable selection is critical in medical prediction models to identify important risk factors while maintaining interpretability. Two statistical frameworks, frequentist and Bayesian, offer distinct approaches. This study systematically compares the two frameworks in the logistic regression context using heart disease prediction as a case study. We analyzed the Cleveland Heart Disease dataset (n=303, 13 predictors) using both approaches. Both methods show strong agreement, selecting five core predictors (ca,cp, thal, sex, oldpeak) with inclusion probabilities larger than 0.5. The methods disagreed only on two marginal predictors. The choice between methods depends on specific inference goals and computational resources. As computational assessment reveals that the frequentist approach is 3-4x faster, we fit a final model using the frequentist approach.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Grzegorczyk, M.A. and Krijnen, W.P. |
| Degree programme: | Mathematics |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 26 Nov 2025 13:12 |
| Last Modified: | 26 Nov 2025 13:12 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/37148 |
Actions (login required)
 |
View Item |