When dealing with statistical analysis and probabilities its often the missing information that can be an issue. This can result in bias when working in areas such as reliability, data science and machine learning that result in incorrect solutions. We’ve seen that in such things as the percentage of type of motor failures, faulty IoT devices, false positives and negatives in healthcare and prognostic software, and other studies. The assumptions make sense from what appears to be common sense, but often that remains part of the bias that is used to reinforce our perception of reality and repetition of the same errors.
Reliability-Engineering-1