Please use this identifier to cite or link to this item:
|Authors:||SALTELLI Andrea; ANNONI Paola|
|Type:||Articles in books|
|Abstract:||Existing guidelines for impact assessment recommend that mathematical modelling of real or man-made system be accompanied by a `sensitivity analysis' - SA (EC, 2009; EPA, 2009; OMB, 2006). The same recommendation can be found in textbooks for practitioners (e.g. Kennedy, 2007, Saltelli et al., 2008). Mathematical models can be seen as machines capable of mapping from a set of assumptions (data, parameters, scenarios) into an inference (model output). In this respect modellers should tackle: - Uncertainty. Characterize the empirical probability density function and the condence bounds for a model output. This can be viewed as the numerical equivalent of the measurement error for physical experiments. The question answered is "How uncertain is this inference?". - Sensitivity. Identify factors or groups of factors mostly responsible for the uncertainty in the prediction. The question answered is "Where is this uncertainty coming from?". The two terms are often used differently, with sensitivity analysis used for both challenges (e.g. Leamer, 1990). We focus on sensitivity analysis proper, i.e. the effect of individual factors or group of factors in driving the output and its uncertainty.|
|JRC Institute:||Institute for the Protection and Security of the Citizen|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.