Normalizing Quantitative Traits with Empirical Normal Quantile Transformation
Author Information
Author(s): Peng Bo, Yu Robert K, DeHoff Kevin L, Amos Christopher I
Primary Institution: The University of Texas, M.D. Anderson Cancer Center
Hypothesis
Can empirical normal quantile transformation effectively normalize a large number of quantitative traits for better analysis?
Conclusion
The empirical normal quantile transformation (ENQT) significantly improves the analysis of quantitative traits by maintaining power and controlling type I error.
Supporting Evidence
- ENQT transformation achieves similar power to perfect back-transformation while controlling type I error.
- Nearly half of the traits in the GAW15 data set failed normality tests before transformation.
- ENQT is computationally efficient and can be applied to all quantitative traits.
Takeaway
This study shows a new way to make data about traits easier to understand and analyze, which helps scientists find important information without getting confused by too much data.
Methodology
The study used simulations to test the impact of ENQT on power and type I error, and applied it to real data from the Genetic Analysis Workshop 15.
Limitations
The method may not perform as well as customized transformations for each trait and could discard delicate within-family structures.
Participant Demographics
194 individuals from 14 families with 3554 traits and 2882 SNP markers.
Statistical Information
Statistical Significance
p<0.05
Want to read the original?
Access the complete publication on the publisher's website