Using Hierarchical Modeling in Genetic Studies
Author Information
Author(s): Liu Xin, Jorgenson Eric, Witte John S
Primary Institution: University of California, San Francisco
Hypothesis
Can hierarchical modeling improve the accuracy of genetic association studies involving multiple phenotypes?
Conclusion
Hierarchical modeling slightly increases the power to detect true associations while reducing false positives in genetic studies.
Supporting Evidence
- Hierarchical modeling led to fewer false positives compared to conventional methods.
- The power to detect true associations was slightly higher with hierarchical modeling.
- Phenotypes were grouped into three clusters based on clinical characteristics.
Takeaway
This study shows that using a special method called hierarchical modeling can help scientists find real links between genes and diseases while making fewer mistakes.
Methodology
The study used a simulated dataset to compare hierarchical modeling with conventional logistic regression in analyzing genetic associations.
Limitations
The study did not use the 'truth' for simulations, which may affect the validity of the results.
Participant Demographics
350 cases and 700 controls from four populations.
Statistical Information
P-Value
<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website