Engineering statistics uncertainty, estimation

As with troubleshooting, parameter estimation is not an exact science. The facade of statistical and mathematical routines coupled with sophisticated simulation models masks the underlying uncertainties in the measurements and the models. It must be understood that the resultant parameter values embody all of the uncertainties in the measurements, underlying database, and the model. The impact of these uncertainties can be minimized by exercising sound engineering judgment founded upon a famiharity with unit operation and engineering fundamentals. 

QRA is fundamentally different from many other chemical engineering activities (e.g., chemistry, heat transfer, reaction kinetics) whose basic property data are theoretically deterministic. For example, the physical properties of a substance for a specific application can often be established experimentally. But some of the basic property data used to calculate risk estimates are probabilistic variables with no fixed values. Some of the key elements of risk, such as the statistically expected frequency of an accident and the statistically expected consequences of exposure to a toxic gas, must be determined using these probabilistic variables. QRA is an approach for estimating the risk of chemical operations using the probabilistic information. And it is a fundamentally different approach from those used in many other engineering activities because interpreting the results of a QRA requires an increased sensitivity to uncertainties that arise primarily from the probabilistic character of the data. 

Safety factors are used in engineering design to reduce the design load (or equivalent parameter) to allow for the predicted degradation, to allow for a confidence limit based on statistical evaluation, or to allow simply for uncertainty. It is clear that any predicted degradation should be allowed for in full. Confidence limits can be calculated. Uncertainties must be estimated. For example, to allow for the extrapolation necessary... 

The analysis of the ECS phase of the accident is based on a combination of bounding best estimate for loop flows and a mechanistic modeling and engineering approach for phenomena within the fuel assembly. Because of the nature of the uncertainties and the lack of prototype experimental data to perform a detailed statistical analysis comparable to that performed for FI, ECS uncertainties have been classified as biases and random uncertainties and treated in a conventional manner. Thus, the methodology is still evolving in... 

---