Package: maxstablePCA 0.1.1
Felix Reinbott
maxstablePCA: Apply a PCA Like Procedure Suited for Multivariate Extreme Value Distributions
Dimension reduction for multivariate data of extreme events with a PCA like procedure as described in Reinbott, Janßen, (2024), <doi:10.48550/arXiv.2408.10650>. Tools for necessary transformations of the data are provided.
Authors:
maxstablePCA_0.1.1.tar.gz
maxstablePCA_0.1.1.tar.gz(r-4.5-noble)maxstablePCA_0.1.1.tar.gz(r-4.4-noble)
maxstablePCA_0.1.1.tgz(r-4.4-emscripten)maxstablePCA_0.1.1.tgz(r-4.3-emscripten)
maxstablePCA.pdf |maxstablePCA.html✨
maxstablePCA/json (API)
| # Install 'maxstablePCA' in R: |
| install.packages('maxstablePCA', repos = 'https://cloud.r-project.org') |
This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.
Last updated 7 months agofrom:857a81872c. Checks:3 OK. Indexed: yes.
| Target | Result | Latest binary |
|---|---|---|
| Doc / Vignettes | OK | Mar 07 2025 |
| R-4.5-linux-x86_64 | OK | Mar 07 2025 |
| R-4.4-linux-x86_64 | OK | Mar 07 2025 |
Exports:compressmax_stable_prcompmaxmatmulreconstructtransform_orig_marginstransform_unitfrechettransform_unitpareto
Dependencies:nloptr
Citation
To cite package ‘maxstablePCA’ in publications use:
Reinbott F (2024). maxstablePCA: Apply a PCA Like Procedure Suited for Multivariate Extreme Value Distributions. R package version 0.1.1, https://CRAN.R-project.org/package=maxstablePCA.
Corresponding BibTeX entry:
@Manual{,
title = {maxstablePCA: Apply a PCA Like Procedure Suited for
Multivariate Extreme Value Distributions},
author = {Felix Reinbott},
year = {2024},
note = {R package version 0.1.1},
url = {https://CRAN.R-project.org/package=maxstablePCA},
}
Readme and manuals
maxstablePCA
A package for dimensionality reduction of multivariate extremes using the idea of PCA to obtain a resonable compact description of the data.
Main functionalities
- Transform a dataset to standard margins to use well known ideas from extreme value theory
- Perform a dimensionality reduction of a dataset to a fixed number of encoding variables. For further information about the theory of this consider looking at the references.
- Evaluate the quality of this reconstruction.
- Transform the data back to the distribution of the original dataset.
Examples on simulated and real world data
For a better feeling of what this algorithm does, please consider looking at the following repo, providing example data analyses and simulation studies https://github.com/FelixRb96/maxstablePCA_examples.
References
- Principal component analysis for max-stable distributions, Reinbott F., Janßen A. , arxiv preprint, https://arxiv.org/abs/2408.10650
- A semi-group approach to Principal Component Analysis, Schlather M., Reinbott F., arxiv preprint, https://arxiv.org/pdf/2112.04026.pdf, 2021
Help Manual
| Help page | Topics |
|---|---|
| Transform data to compact representation given by max-stable PCA | compress |
| Calculate max-stable PCA with dimension p for given dataset | max_stable_prcomp |
| Multiply two matrices with a matrix product that uses maxima instead of addition | maxmatmul |
| Obtain reconstructed data for PCA | reconstruct |
| Print summary of a max_stable_prcomp object. | summary.max_stable_prcomp |
| Transform the columns of a transformed dataset to original margins | transform_orig_margins |
| Transform the columns of a dataset to (approximately) unit Frechet margins | transform_unitfrechet |
| Transform the columns of a dataset to unit Pareto | transform_unitpareto |