Bayesian networks are often used in problem domains that include variables of a continuous nature. For capturing such variables, their value ranges basically have to be modelled as finite sets of discrete values. While the output probabilities and conclusions established from a network are dependent of the actual discretisations used for its variables, the effects of choosing alternative discretisations are largely unknown as yet. This paper describes the first steps of a study into the effects of changing discretisations on the probability distributions computed from a Bayesian network. We focus more specifically on the feature variables of a naive Bayesian network and demonstrate how insights from the research area of sensitivity analysis can be exploited for studying how the network’s output is affected by alternative discretisations.