APEMoST documentation – Bayesian inference using MCMC

Automated Parameter Estimation and Model Selection Toolkit

APEMoST is a free, fast MCMC engine that allows the user to apply Bayesian inference for parameter estimation and model selection.

Quick links:

1. General information

   What is APEMoST? What is Bayesian Inference?

2. User manual

   Includes how to get APEMoST.

3. FAQ. Also see here for contact details.

Full Table of Contents:

• Automated Parameter Estimation and Model Selection Toolkit (APEMoST)
  • Specification
  • Fundamentals
  • Features
• User Manual
  • Prerequisites
  • Getting APEMoST
  • The general concept
  • Phase 0 - Preparation
  • Phase 1 - Calibration, first chain (beta = 1)
  • Phase 1 - Calibration, other chains (beta <= 1)
  • Phase 2 - Running
  • Phase 3 - Analyse
  • Hacking APEMoST
  • Other topics
  • Concluding remarks
• FAQ - Frequently Asked Questions
• License
• Links and other software
  • Introduction to MCMC and Bayesian inference
  • Differences and other programs

You can download the full documentation (PDF). Also available is the API reference (HTML) or (PDF).

News:

You can now access and write your likelihood functions in C, C++ and Python!

• Check out the PyAPEMoST project hosted together with PyMultiNest.

New Publication using APEMoST:

• “Gamma-ray bursts as cosmological probes: LambdaCDM vs. conformal gravity” Antonaldo Diaferio et al, 2011