Mixed-effects Cox models of alcohol dependence in extended families
Author Information
Author(s): Zhao Jinghua, Joan E Bailey-Wilson, Laura Almasy, Mariza de Andrade, Julia Bailey, Heike Bickeböller, Heather J Cordell, E Warwick Daw, Lynn Goldin, Ellen L Goode, Courtney Gray-McGuire, Wayne Hening, Gail Jarvik, Brion S Maher, Nancy Mendell, Andrew D Paterson, John Rice, Glen Satten, Brian Suarez, Veronica Vieland, Marsha Wilcox, Heping Zhang, Andreas Ziegler, Jean W MacCluer
Primary Institution: University College London
Hypothesis
Can a mixed-effects Cox model effectively analyze familial correlations in alcohol dependence data?
Conclusion
The study found that the mixed-effects Cox model can provide valuable insights into the genetic and environmental factors influencing alcohol dependence.
Supporting Evidence
- The study utilized data from the Collaborative Study on the Genetics of Alcoholism.
- Results indicated that familial relationships significantly influence alcohol dependence.
- The mixed-effects model showed improved fit compared to standard Cox models.
- Significant variance estimates were found for specific genetic markers.
- False-discovery rates were calculated to assess the reliability of findings.
Takeaway
This study looks at how family relationships can help us understand alcohol dependence better by using a special statistical model.
Methodology
The study used a mixed-effects Cox model to analyze microsatellite data from families with alcohol dependence.
Potential Biases
Potential bias due to the non-positive definite IBD matrices and the exclusion of certain data.
Limitations
The analysis did not adjust for ethnicity and relied on specific definitions of alcoholism.
Participant Demographics
The sample included 1,614 individuals from 143 families, with 826 men and 788 women.
Statistical Information
P-Value
0.012
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website