In flood frequency applications where the design flood is required to have
a specified exceedance probability, expected probability should be used. It
s computation, however, presents formidable difficulties. This study presen
ts a Monte Carlo Bayesian method for computing the expected probability dis
tribution as well as quantile confidence limits for any flood frequency dis
tribution using data on gauged flows, possibly corrupted by rating curve er
ror, and on censored flows. This is achieved by a three-step process: (1) F
ormulate the likelihood function for the given data; (2) approximate the li
kelihood function using a multinormal distribution; and (3) integrate the e
xpected probability integral using importance sampling. The FLIKE software
for performing this is described, and an example is given.