jameschapman19 / scikit-palm

Implementing permutation methods for multiview learning in python
BSD 3-Clause "New" or "Revised" License
4 stars 0 forks source link

Python package codecov Scrutinizer Code Quality

scikit-perm

Implementing the PALM — Permutation Analysis of Linear Models toolbox (https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/PALM) for Python. PALM a

Documentation

Further documentation is hosted at https://scikit-perm.readthedocs.io/en/latest/

Objectives

The goal is to have a flexible framework for statistically valid permutation testing when using linear models from https://github.com/scikit-learn/scikit-learn or otherwise.

The framework should also be adaptable to multiview models such as those in https://github.com/mvlearn/mvlearn

Project is open to contributions.

I am currently aware of some related repos e.g. https://github.com/danlurie/PyPALM https://github.com/statlab/permute but neither appear to contain the functionality for multi-level exchangeability block permuation.

References

The authors of PALM https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/PALM https://github.com/andersonwinkler/PALM give the following references:

The main reference for PALM:

For correction across contrasts:

For Non-Parametric Combination, classical multivariate tests (MANOVA, MANCOVA), assessed with permutations, and for correction over contrasts and/or modalities:

For the multi-level exchangeability blocks:

For the accelerated permutation inference:

For additional theory of permutation tests in neuroimaging: