Model Calibration

Calibrate graph models from observations

After creating a graph, conditional probability distribution parameters can be calibrated using historical data or reflecting expert judgement.



  • Several optimization techniques available.

  • Start simple with regression under linear assumptions on node dependencies.

  • Incorporate expert judgment in parameterizing nodes distributions.

  • Data imputation techniques available for incomplete datasets.

  • Frequency matching.

  • Preprocessing methods available prior to calibration.

  • Data transformation routines. Node types: Categorical, Discrete, Continuous, Mixture, Deterministic.


  • Koller D, Friedman N. Probabilistic graphical models: principles and techniques. MIT press; 2009.
  • Sucar LE. Probabilistic graphical models. Advances in Computer Vision and Pattern Recognition. London: Springer London. doi. 2015;10(978):1.
  • Darwiche A. Modeling and reasoning with Bayesian networks. Cambridge university press; 2009 Apr 6. - 17 Learning: The Maximum Likelihood Approach p439, 18 Learning: The Bayesian Approach p477
spinner image
Loading resources

Get TKRISK Today

Instant Access

Get started with your free trial account.