hierarch is a Python package for hierarchical resampling of datasets. It leverages the use of Numba for speeding up key functionalities and is designed with a focus on performance, scalability, and usability.
- Hierarchical Resampling: Includes bootstrapping and permutation of datasets.
- Statistical Tools: Helps perform resampling-based hypothesis tests, confidence interval calculations, and power analyses on hierarchical data.
- Automated Tests: Enables automated design-based randomization tests for experiments with varying levels of hierarchy.
The source code for
hierarch is available on GitHub.
Installation is easy and can be done via PyPi or Anaconda.
pip install hierarch
conda install -c rkulk111 hierarch
Detailed user guide and documentation can be found at readthedocs.
Hierarch was published in PLoS Computational Biology. If you use Hierarch in your research, please cite:
Kulkarni RU, Wang CL, Bertozzi CR (2022) Analyzing nested experimental designs—A user-friendly resampling method to determine experimental significance. PLoS Comput Biol 18(5): e1010061. https://doi.org/10.1371/journal.pcbi.1010061