Comparing uncertainties—Are they really different?

Uncertainties occur at all stages of a measurement process. Quantification of these uncertainties is important in order to make reliable decisions based on these measurement results. In some cases it can be useful to be able to compare the uncertainties associated with different measurement methods, in order to establish the method that is most reliable. A comparison can also be made between uncertainties that have themselves been evaluated using different estimation procedures. This paper discusses the comparison of uncertainties in chemical measurements using case study examples. Depending on the context, both exact and approximate F-tests are used to compare the ratios of uncertainties, while in some cases the approach is to compare separate confidence intervals.