CARMA: A platform for analyzing microarray datasets
Author Information
Author(s): Kevin A Greer, Matthew R McReynolds, Heddwen L Brooks, James B Hoying
Primary Institution: University of Arizona
Hypothesis
Can CARMA improve the analysis of microarray datasets by incorporating statistical models that account for experimental variability?
Conclusion
CARMA effectively reduces the number of genes incorrectly identified as differentially expressed and results in a more robust and reliable analysis.
Supporting Evidence
- CARMA provides a clear quantitative and statistical characterization of each measured gene.
- Applying CARMA improves estimates of differences in gene expression.
- CARMA can accommodate missing data and perform outlier detection.
Takeaway
CARMA is a tool that helps scientists analyze gene data from experiments more accurately, making it easier to see which genes are really different between samples.
Methodology
CARMA performs ANOVA on microarray datasets, normalizes data, detects outliers, and accommodates missing data.
Potential Biases
Potential bias from background subtraction and transformation methods that may inflate variance.
Limitations
The implementation of CARMA assumes normal distribution of data after applying the linear model and may not account for all sources of variability.
Participant Demographics
Adult aquaporin-1 knockout and wild type mice.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website