Evaluating Regression Models for Breast Cancer Data
Author Information
Author(s): Abo El Nasr Mona Mahmoud, Abdelmegaly Alaa A., Abdo Doaa A.
Primary Institution: Mansoura University
Hypothesis
How do different regression models perform in analyzing breast cancer patient data?
Conclusion
The study found that the Beta regression model outperformed others based on the Bayesian Information Criterion (BIC), while the Ridge regression model showed superiority according to the Akaike Information Criterion (AIC).
Supporting Evidence
- The Beta regression model achieved a BIC of -5520.416.
- The Ridge regression model demonstrated the best AIC at -8002.647.
- The study utilized data from the Breast Cancer Wisconsin Diagnostic dataset.
Takeaway
This study looked at different math models to understand breast cancer data, and found that some models work better than others.
Methodology
The study compared various regression models including Beta regression, Ridge regression, and Generalized Additive Models (GAM) using real data and simulations.
Limitations
The conclusions are drawn within the confines of the study’s dataset and simulation parameters, which may not be generalizable.
Participant Demographics
The dataset comprises records from 569 breast cancer patients.
Statistical Information
P-Value
<2.0e-16
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website