Analyzing Alcoholism Data with Support Vector Machines
Author Information
Author(s): Yu Robert, Shete Sanjay
Primary Institution: The University of Texas M. D. Anderson Cancer Center
Hypothesis
Support vector machine (SVM) is an ideal method to analyze the alcoholism dataset provided by COGA.
Conclusion
The study demonstrates that SVM is effective in recognizing marker patterns and predicting phenotypic traits in alcoholism data.
Supporting Evidence
- The SVM achieved high levels of correctness in predictions, with up to 96% accuracy in cross-validations.
- Positive results were observed in various analyses of phenotype variables using SVM.
- The study identified specific chromosome regions associated with the ALDX phenotype trait.
Takeaway
Researchers used a computer program to look at genetic data related to alcoholism, and they found that this method can help identify important patterns.
Methodology
The study used support vector machines to analyze a dataset of microsatellite markers and phenotype variables.
Potential Biases
The SVM may struggle with imbalanced data and noise, which could lead to incorrect classifications.
Limitations
The study faced limitations due to the small sample size and the inability to test predictions on new data.
Participant Demographics
The dataset included individuals with various alcoholism-related traits, but specific demographics were not detailed.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website