Using Propensity Scores to Improve Linkage Analysis for Alcoholism
Author Information
Author(s): Betty Q Doan, Constantine E Frangakis, Yin Y Shugart, Joan E Bailey-Wilson
Primary Institution: Johns Hopkins Bloomberg School of Public Health
Hypothesis
Can the use of propensity scores improve the power to detect linkage in genetic studies of alcoholism?
Conclusion
The study found that using a propensity score can increase the power to detect genetic linkage for alcoholism.
Supporting Evidence
- Using a propensity score can lead to more significant markers identified compared to using all covariates simultaneously.
- The study identified significant chromosomal regions associated with alcoholism.
- PS3, which includes age, sex, and smoking status, resulted in the greatest number of significant markers.
Takeaway
This study shows that combining different factors into one score can help scientists find genes related to alcoholism more easily.
Methodology
The study used genome-wide linkage analysis with various covariates and propensity scores to evaluate linkage evidence.
Limitations
The presence of observed covariate data on both affected and unaffected individuals is required, which may not always be available.
Participant Demographics
Families ascertained by the Collaborative Study on the Genetics of Alcoholism.
Statistical Information
P-Value
0.0044
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website