ECDF-based Distance Measure Algorithms
Updated 29 Apr 2020
A set of functions for well-known Empirical Cumulative Distribution Function (CDF)-based distance measure.
Statistical/Probabilistic distance measure algorithms can be categorized into two main categories I) Cumulative Distribution Function (CDF)-based and Probability Density Function (PDF)-based. The following algorithms have been implemented:
- Wasserstein Distance
- Anderson-Darling Distance
- Kolmogorov Smirnov Distance
- Cramer von Mises Distance
- Kuiper Distance
- Wasserstein-Anderson-Darling Distance
The code has been converted to MATLAB from "twosamples" library of R (https://github.com/cdowd/twosamples).
This framework is available under an MIT License.
Koorosh Aslansefat (2020). ECDF-based Distance Measure Algorithms (https://www.github.com/koo-ec/CDF-based-Distance-Measure), GitHub. Retrieved April 29, 2020.
Koorosh Aslansefat (2022). ECDF-based Distance Measure Algorithms (https://github.com/koo-ec/ECDF-based-Distance-Measure/releases/tag/v1.1), GitHub. Retrieved .
Aslansefat, Koorosh, et al. “SafeML: Safety Monitoring of Machine Learning Classifiers Through Statistical Difference Measures.” Model-Based Safety and Assessment, Springer International Publishing, 2020, pp. 197–211, doi:10.1007/978-3-030-58920-2_13.
MATLAB Release Compatibility
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!