Multifidelity estimation combines the output of simulation models of different approximation quality and from different sources in order to obtain efficient estimators for a quantity of interest. In this contribution, possibilities to establish model hierarchies are investigated. Once a model hierarchy is established, the outputs of the models must be combined by information fusion and/or information filtering. To this end, importance sampling is extended to model hierarchies by introducing

more »

... tive as well as multiplicative information fusion. The multi-fidelity reliability estimation methods are compared and critically assessed based on a simple example that highlights the main features of the methods.