Discretisation Effects in Naive Bayesian Networks

  • Roel Bertens
  • Linda C. van der Gaag
  • Silja Renooij
Part of the Communications in Computer and Information Science book series (CCIS, volume 299)


Naive Bayesian networks are often used for classification problems that involve variables of a continuous nature. Upon capturing such variables, their value ranges are modelled as finite sets of discrete values. While the output probabilities and conclusions established from a Bayesian network are dependent of the actual discretisations used for its variables, the effects of choosing alternative discretisations are largely unknown as yet. In this paper, we study the effects of changing discretisations on the probability distributions computed from a naive Bayesian network. We demonstrate how recent insights from the research area of sensitivity analysis can be exploited for this purpose.


Bayesian Network Feature Variable Sensitivity Function Class Variable Joint Probability Distribution 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dougherty, J., Kohavi, R., Sahami, M.: Supervised and unsupervised discretization of continuous features. In: Russel, S.J. (ed.) Proceedings of the 12th International Conference on Machine Learning, pp. 194–202. Morgan Kaufmann, CA (1995)Google Scholar
  2. 2.
    Uusitalo, L.: Advantages and challenges of Bayesian networks in environmental modelling. Ecological Modelling 203, 312–318 (2007)CrossRefGoogle Scholar
  3. 3.
    Myllymäki, P., Silander, T., Tirri, H., Uronen, P.: B-Course: a web-based tool for Bayesian and causal data analysis. International Journal of Artificial Intelligence Tools 11, 369–387 (2002)CrossRefGoogle Scholar
  4. 4.
    Coupé, V.M.H., van der Gaag, L.C.: Properties of sensitivity analysis of Bayesian belief networks. Annals of Mathematics and Artificial Intelligence 36, 323–356 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    van der Gaag, L.C., Renooij, S., Coupé, V.M.H.: Sensitivity analysis of probabilistic networks. In: Lucas, P., Gámez, J., Salmerón, A. (eds.) Advances in Probabilistic Graphical Models. STUDFUZZ, vol. 214, pp. 103–124. Springer, NY (2007)CrossRefGoogle Scholar
  6. 6.
    Kjærulff, U., van der Gaag, L.C.: Making sensitivity analysis computationally efficient. In: Boutilier, C., Goldszmidt, M. (eds.) Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, pp. 317–325. Morgan Kaufmann, CA (2000)Google Scholar
  7. 7.
  8. 8.
    Dawson-Saunders, B., Trapp, R.G.: Basic & Clinical Biostatistics. McGraw-Hill, NY (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Roel Bertens
    • 1
  • Linda C. van der Gaag
    • 1
  • Silja Renooij
    • 1
  1. 1.Department of Information and Computing SciencesUtrecht UniversityThe Netherlands

Personalised recommendations