PTC22 sys: "Both pre- and post-test uncertainty calculations
are required." and "The number of locations and frequency of measurements shall be determined by the pre-test uncertainty analysis."
Is any body knows any instructions to calculate pre-test uncertainty?
You could consult texts and articles of DOE (design of experiments).
Pre-test uncertainty analysis is essential. Outline your experiment and evaluate the factors that must be controlled. Estimate the uncertainties and plan for need to control. The variances are summed as
VT = V1+V2+V3+ ...
Divide by VT with the variances in descending order, V1>V2> ...
Plan and design sampling based on contribution of variance. Large contributions require the most control. Small contributions the least or no control (
You do not need to do this imo. Instead, you should focus on the design of your experiment, sample size, statistical power, etc. But when you analyse your data, it will naturally contain estimates of uncertainty such as standard error, standard deviation, etc.
There is no quick answer to this question, although it does seem to strike at the heart of the problem as far as practical measurements are concerned. To see this, a very useful read would be for example
Article Adaptive multiscale predictive modelling
I also recommend this lecture by Prof. Tinsley Oden
https://vimeo.com/102636357
Good luck with your quest!
- Badges
- Science topic
- Similar topics
- Higher Education
- Universities