The -Version of the Cramér-von Mises Test for Two-Sample Comparisons in Microarray Data Analysis
2006
New Test for Comparing Microarray Data
publication
Evidence: moderate
Author Information
Author(s): Yuanhui Xiao, Gordon Alexander, Andrei Yakovlev
Primary Institution: University of Rochester
Hypothesis
The study investigates the performance of a new statistical test for comparing two samples in microarray data analysis.
Conclusion
The new -distance test is nearly as powerful as the Cramér-von Mises test but requires less computational resources.
Supporting Evidence
- The -distance test allows for larger sample sizes compared to the Cramér-von Mises test.
- The new test is based on a distance between two empirical distribution functions.
Takeaway
Researchers created a new way to compare data from two groups of genes that is easier to use than the old method.
Methodology
The study compares the performance and power of the -distance test with the Cramér-von Mises test and other classical tests using simulated and real microarray data.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website