7. The Calibration module

• 7.1. Brief reminder of theoretical aspects
  • 7.1.1. Distances and likelihoods used to compare observations and model predictions
  • 7.1.2. Discussing assumptions and theoretical background
    • 7.1.2.1. Calibration in the context of VVUQ principle
    • 7.1.2.2. Interest in the least square measurement
    • 7.1.2.3. Introduction to Bayesian approach
• 7.2. Using minimisation techniques
• 7.3. Analytical linear Bayesian estimation
  • 7.3.1. Prediction values
• 7.4. Approximate Bayesian Computation techniques (ABC)
  • 7.4.1. Rejection ABC algorithm
• 7.5. Markov chain Monte Carlo approach
  • 7.5.1. Markov chain principle
  • 7.5.2. The MCMC algorithms
    • 7.5.2.1. Metropolis-Hastings algorithm
    • 7.5.2.2. Component-wise Metropolis-Hastings
  • 7.5.3. Assessing convergence
• 7.6. CIRCE method
  • 7.6.1. Main principle of the CIRCE method
    • 7.6.1.1. The linearity hypothesis
    • 7.6.1.2. The normality hypothesis