foxi: Forecast Observations and their eXpected Information

Discussion topics for individual codes
Post Reply
Ada Coda
ASCL Robot
Posts: 2069
Joined: Thu May 08, 2014 5:37 am

foxi: Forecast Observations and their eXpected Information

Post by Ada Coda » Sat Jun 30, 2018 8:49 am

foxi: Forecast Observations and their eXpected Information

Abstract: Using information theory and Bayesian inference, the foxi Python package computes a suite of expected utilities given futuristic observations in a flexible and user-friendly way. foxi requires a set of n-dim prior samples for each model and one set of n-dim samples from the current data, and can calculate the expected ln-Bayes factor between models, decisiveness between models and its maximum-likelihood averaged equivalent, the decisivity, and the expected Kullback-Leibler divergence (i.e., the expected information gain of the futuristic dataset). The package offers flexible inputs and is designed for all-in-one script calculation or an initial cluster run then local machine post-processing, which should make large jobs quite manageable subject to resources and includes features such as LaTeX tables and plot-making for post-data analysis visuals and convenience of presentation.

Credit: Hardwick, Robert J.


Bibcode: 2018ascl.soft06030H

Preferred citation method:

ID: ascl:1806.030
Last edited by Ada Coda on Sun Oct 04, 2020 8:52 pm, edited 1 time in total.
Reason: Updated code entry.

Post Reply