Permutation – based statistical tests for multiple hypotheses
2008

Ptest: A Software for Permutation-Based Statistical Tests

Sample size: 34 publication 10 minutes Evidence: moderate

Author Information

Author(s): Anyela Camargo, Francisco Azuaje, Haiying Wang, Huiru Zheng

Primary Institution: University of East Anglia

Hypothesis

Can permutation-based statistical tests improve the accuracy of hypothesis testing in genomics and proteomics?

Conclusion

The software developed can effectively support a wide range of hypothesis testing tasks in functional genomics.

Supporting Evidence

  • The software allows for the calculation of Chi-square tests for categorical data.
  • It implements Bonferroni and Benjamini and Hochberg corrections for Type I error control.
  • The tool is user-friendly and open-source, making it accessible for researchers.

Takeaway

This study created a tool that helps scientists test many ideas at once without making mistakes, like saying something is true when it's not.

Methodology

The software calculates test statistics for categorical and numerical data and validates significance using various statistical tests.

Potential Biases

Potential for Type I and Type II errors if not used correctly.

Limitations

The software may not cover all possible statistical tests and relies on user input for data formatting.

Participant Demographics

The study included samples from African-American, European-American, and Han-Chinese populations.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1751-0473-3-15

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication