BayesFit: A Tool for Modeling Psychophysical Data Using Bayesian Inference. Issue 1 (17th January 2019)

• Record Type: Journal Article
• Authors: Slugocki, Michael; Sekuler, Allison B.; Bennett, Patrick J.
• Is Part Of: Journal of open research software. Volume 7:Issue 1(2019)
• Publication Date: 2019-01-17
• Subjects: Psychophysics -- Psychometrics -- Psychometric function -- Bayesian inference -- Numerical integration -- Curve fitting -- Python; Computer software -- Reusability -- Periodicals; Open source software -- Periodicals; 005
• DOI: 10.5334/jors.202
• Languages: English
• ISSNs: 2049-9647

Abstract

BayesFit is a module for Python that allows users to fit models to psychophysical data using Bayesian inference. The module aims to make it easier to develop probabilistic models for psychophysical data in Python by providing users with a simple API that streamlines the process of defining psychophysical models, obtaining fits, extracting outputs, and visualizing fitted models. Our software implementation uses numerical integration as the primary tool to fit models, which avoids the complications that arise in using Markov Chain Monte Carlo (MCMC) methods [1 ]. The source code for BayesFit is available athttps://github.com/slugocm/bayesfit and API documentation athttp://www.slugocm.ca/bayesfit/ . This module is extensible, and many of the functions primarily rely on Numpy [2 ] and therefore can be reused as newer versions of Python are developed to ensure researchers always have a tool available to ease the process of fitting models to psychophysical data.