PreliZ
An editor has nominated this article for deletion. You are welcome to participate in the deletion discussion, which will decide whether or not to retain it. |
 | This article is an orphan, as no other articles link to it. Please introduce links to this page from related articles; try the Find link tool for suggestions. (November 2024) |
| Original author(s) | ArviZ Development Team |
|---|---|
| Initial release | September 21, 2023 |
| Repository | github |
| Written in | Python |
| Operating system | Unix-like, macOS, Windows |
| Platform | Intel x86 – 32-bit, x64 |
| Type | Statistical package |
| License | Apache License, Version 2.0 |
| Website | preliz |
PreliZ is a Python package for exploring and eliciting probability distributions. While it is primarily focused on prior elicitation—the process of converting domain-specific knowledge into well-defined probability distributions—it can also be used to analyze distributions outside the context of Bayesian statistics.[1][2][3][4]
PreliZ is an open source project developed by the community and it is part of the ArviZ family of packages.
Etymology
[edit] |
PreliZ is a word play, relating Prior elicitation with the iZ particle to make the connection with its sister project ArviZ.
Library features
[edit] |
PreliZ provides diverse features for exploring probability distributions and elicit priors [5][6].
- A wide array of probability distributions with associated methods including PDF, CDF, PPF, random sampling, moments, Credible interval (highest density and equally-tailed intervals) etc.
- Many distributions support more than one parameterization.
- Easy visualisation with KDEs, histograms, ecdf.
- Methods for unidimentional elicitation, like, roulette, maximum entropy, quartiles, etc.
- Methods for predictive elictitation.
- Interactive and graphical methods.
- Interface with PyMC, Bambi and potentially other PPLs.
References
[edit]- ^ Icazatti, Alejandro; Abril-Pla, Oriol; Klami, Arto; Martin, Osvaldo A. (2023). "PreliZ: A tool-box for prior elicitation". Journal of Open Source Software. 8 (89): 5499. doi:10.21105/joss.05499.
- ^ Zivich, Paul N.; Edwards, Jessie K.; Shook-Sa, Bonnie E.; Lofgren, Eric T.; Lessler, Justin; Cole, Stephen R. (2024). "Synthesis estimators for positivity violations with a continuous covariate". Journal of the Royal Statistical Society Series A: Statistics in Society. arXiv:2311.09388.
- ^ Mikkola, Petrus; Martin, Osvaldo A.; Chandramouli, Suyog; Hartmann, Marcelo; Abril Pla, Oriol; Thomas, Owen; Pesonen, Henri; Corander, Jukka; Vehtari, Aki; Kaski, Samuel; Bürkner, Paul-Christian; Klami, Arto (2024). "Prior Knowledge Elicitation: The Past, Present, and Future". Bayesian Analysis. 19 (4). International Society for Bayesian Analysis: 1129–1161. arXiv:2112.01380. doi:10.1214/23-BA1381.
- ^ Martin, Osvaldo (2024). Bayesian Analysis with Python - Third Edition: A practical guide to probabilistic modeling. Packt Publishing Ltd. ISBN 9781805127161.
- ^ Icazatti, Alejandro; Abril-Pla, Oriol; Klami, Arto; Martin, Osvaldo A. (2023). "PreliZ: A tool-box for prior elicitation". Journal of Open Source Software. 8 (89): 5499. doi:10.21105/joss.05499.
- ^ Icazatti, Alejandro; Abril-Pla, Oriol; Klami, Arto; Martin, Osvaldo A. (2024). "PreliZ: A tool-box for prior elicitation". Zenodo. doi:10.5281/zenodo.13991977.
External links
[edit]- Official website
- PriorDB a collaborative database of models and their priors