There is a newer version of the record available.

Published September 21, 2015 | Version v0.7.5.7

bumps: v0.7.5.7

Authors/Creators

  • 1. National Institute of Standards and Technology, Gaithersburg, Maryland 20899, USA

Description

Bumps is a program for fitting scientific data using a Bayesian approach. Models are represented as Python functions returning negative log probabilities rather than chi-squared, allowing for a systematic inclusion of prior information from other sources during the fitting process. In addition to returning the best fit using traditional optimization algorithms, Bumps can estimate the joint probability distribution for all fitted parameters using Markov Chain Monte Carlo sampling.

Files

bumps-v0.7.5.7.zip

Files (2.8 MB)

Name Size
md5:808ec872414fcdb7a10912886529dcbd
2.8 MB Preview Download

Additional details

Related works