Value and outcomes
Evidence quality
Also calledConfidence level, Strength of evidence
How much you can trust a claim, judged by who measured it, how, on how many people, and whether anyone can check the source.
Not all statistics are equal. A large, published study with a clear method deserves more weight than a vendor's case study, which deserves more than a number repeated on blogs with no source at all.
A simple grading helps: high confidence for large, methodical, independent studies; medium for credible surveys or partially visible sources; low for small or commissioned studies; unverified for figures no one can trace.
Common mistake
Trusting a number because it appears everywhere. Popular statistics often spread by citation of citations, with no study underneath.