Nonrecurrent congestion in transportation networks occurs as a consequence of stochastic factors affecting demand and supply. Intelligent transportation systems such as advanced traveler information systems and advanced traffic management systems are designed to reduce the impacts of nonrecurrent congestion by providing information to a fraction of users or by controlling the variability of traffic flows. For these reasons, the design of these systems requires a reliable forecast of nonrecurrent congestion. A new method is proposed to measure the impacts of nonrecurrent congestion on travel costs by taking risk aversion into account. The traffic model is based on the dynamic traffic simulation model METROPOLIS. Incidents are generated randomly by reducing the capacity of the network. Users can instantaneously adapt to the unexpected travel conditions or can also change their behavior through a day-to-day adjustment process. Comparisons with incident-free simulations provide a benchmark for potential travel time savings that can be brought about by a state-of-the-art information system. The impact of variable travel conditions is measured by describing the willingness to pay to avoid risky or unreliable journeys. Indeed, for risk-averse drivers, any uncertainty corresponds to a utility loss. This utility loss is computed for several levels of network disruption. The main result of the study is that the utility loss due to uncertainty is of the same order of magnitude as the total travel costs.