In this study we focus on stochastic analysis methods for selective si
mulations, and we consider the extreme midspan moment of a fast-moving
ship subjected to random Gaussian waves. We concentrate on analysis w
ithin a stationary sea state and our purpose is to accurately estimate
hourly maximum ship response (compared with the correct result per ho
ur) within a sea state with as little computational resources as possi
ble. We consider how the use of a limited number of short simulations
with ''critical wave episodes'' (short wave segments which are likely
candidates to produce extreme response in the simulated hour-long hist
ory) reduces the cost of nonlinear time-domain ship response analysis.