A formal Bayesian methodology is presented for integrated model calibration and risk-based water quality management using Bayesian Monte Carlo simulation and maximum likelihood estimation (BMCML).
V. CONCLUSIONS A Bayesian Monte Carlo procedure for nuclear data evaluation has been outlined. The entire information updating procedure has almost been reduced to merely sampling and counting without any reference to assumed Gaussian distributions for either cross sections or model parameters.
The Bayes Monte Carlo method will providesound inference under somevery limited condi-tions. If the parameter space is one-dimensionaland the prior range is similar to the plausibleposterior range of the parameter, ands2is well-chosen, this approach may work.
You can perform Monte Carlo Analysis by analyzing the behavior of random samples taken from an uncertain system. For instance, use usample to obtain an array of numeric models from an uncertain model by sampling the uncertain control design blocks. Generate random samples of uncertain systems from within the modeled uncertainty range.