New Test for Finding Periodicity in Short Time Series Data
Author Information
Author(s): Andrey A. Ptitsyn, Sanjin Zvonic, Jeffrey M. Gimble
Primary Institution: Pennington Biomedical Research Center
Hypothesis
Can a new computational technique effectively identify periodic patterns in short time series data typical of microarray studies?
Conclusion
The Permutated time test (Pt-test) is effective for detecting periodicity in short time series typical for high-density microarray experiments.
Supporting Evidence
- The Pt-test identified 5400 circadially oscillating genes out of 22690 total genes.
- The Pt-test consistently revealed more oscillating genes compared to other algorithms.
- Analysis showed that 20-25% of all genes followed a circadian rhythm.
Takeaway
Scientists created a new test to help find patterns in data that changes over time, like how our bodies have daily rhythms. This test works well even when the data is noisy.
Methodology
The study developed a permutation test that analyzes time series data by randomizing time points to assess periodicity.
Limitations
The algorithm is computationally demanding compared to other methods.
Participant Demographics
Murine liver data from different research institutes.
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