From Quantifying and Propagating Uncertainty to Quantifying and Propagating Both Uncertainty and Reliability: Practice-Motivated Approach to Measurement Planning and Data Processing

When we process data, it is important to take into account that data comes with uncertainty. There exist techniques for quantifying uncertainty and propagating this uncertainty through the data processing algorithms. However, most of these techniques do not take into account that in th real world, measuring instruments are not 100% reliable – they sometimes malfunction and produce values which are far off from the measured values of the corresponding quantities. How can we take into account both uncertainty and reliability? In this paper, we consider several possible scenarios, and we show, for each scenario, what is the natural way to plan the measurements and to quantify and propagate the resulting uncertainty and reliability.