What is it about?
We developed and tested a new method to determine which set of measurements in a series are higher or lower when there are multiple populations to consider. This allowed us to determine which environmental stress combinations (such as drought and lack of fertilizer) worked together and which combinations cancel each other in our experimental dataset, and whether the pattern of cancellation or synergy different in different genotype populations. The new method makes very few assumptions about the samples and factor combinations, which makes the method widely applicable. The method is robust to zero inflated data and missing data.
Featured Image
Why is it important?
Our new method leverage U-statistics to analyze data efficiently and effectively, allowing improved analysis of realistic datasets from an experimental design that is commonly used in biology and the physical sciences.
Perspectives
This study addresses a gap in statistics, as a commonly used experimental design was not matched with an effective analysis method that allowed for realistic sample sizes and sample features such as missing data and zero inflation. We think this is an excellent example of synergy between experimental and statistical scientists.
Ann Stapleton
University of North Carolina Wilmington
Read the Original
This page is a summary of: Two-sample nonparametric stochastic order inference with an application in plant physiology, Journal of Statistical Computation and Simulation, June 2018, Taylor & Francis,
DOI: 10.1080/00949655.2018.1482492.
You can read the full text:
Contributors
The following have contributed to this page
