Definition · Plain-language
Accuracy and precision
Accuracy is how close a measurement is to the true value; precision is how close repeated measurements are to one another — two distinct ideas often confused.
The step most authors miss
Doing CRediT right? Don’t stop at the statement.
A CRediT statement credits you inside one paper. The recognition CRediT was built for happens when those roles are tied to you, persistently. Sign in with your ORCID — free — and claim your CRediT contributions on casrai.org, the home of the standard. They become a verified, portable part of your identity, not a line that disappears into one PDF.
Free: claim your contributions, then export a journal-ready CRediT statement, schema.org structured data, JATS XML, CSV or BibTeX — and preview your public profile. A membership publishes that profile publicly and verifies the journals you serve.
Two different questions
Accuracy and precision answer different questions about a measurement. Accuracy asks: how close is the result to the true value? Precision asks: how close are repeated results to each other? A bathroom scale that always reads two kilograms heavy is precise — it gives the same answer every time — but inaccurate, because that answer is consistently wrong. A scale that scatters readings around the right value is accurate on average but imprecise. The two properties are genuinely independent, which is why a single measurement cannot, on its own, tell you whether it is both.
The dartboard analogy
The standard picture is a dartboard. If your darts land tightly together but far from the centre, you are precise but not accurate — there is a consistent bias pulling you off target. If they scatter widely but average out around the bullseye, you are accurate but not precise — there is a lot of random error. Darts that cluster tightly on the bullseye are both accurate and precise, the ideal. This image makes clear that bias and scatter are separate problems, fixed in different ways: bias by calibration, scatter by better technique or more repeats.
Why both matter in measurement
Reliable measurement needs accuracy and precision together, and they map onto two kinds of error. Systematic error — a consistent bias such as a miscalibrated instrument — harms accuracy and is reduced by calibrating against a known standard. Random error — unpredictable scatter from noise or fluctuating conditions — harms precision and is reduced by averaging repeated measurements. Reporting a result honestly means stating both how close it is likely to be to the truth and how much it varies, which is the role of measurement uncertainty.
Key facts
At a glance
- Accuracy: closeness of a measurement to the true value
- Precision: closeness of repeated measurements to one another
- Independence: a result can be precise but inaccurate, or vice versa
- Accuracy harmed by: systematic error (bias) — fixed by calibration
- Precision harmed by: random error (scatter) — reduced by averaging
- Analogy: the dartboard — bullseye is accuracy, tight grouping is precision
Common misconceptions
What people often get wrong
Often heard: Accuracy and precision mean the same thing.
Actually: They are distinct. Accuracy is closeness to the true value; precision is closeness of repeated readings to each other. A measurement can have one without the other.
Often heard: A very precise measurement must be accurate.
Actually: Not so. Tightly repeatable readings can all be wrong in the same way — for example, a scale biased two kilograms heavy is precise but inaccurate.
Often heard: Taking more measurements always improves accuracy.
Actually: Averaging more readings reduces random error and so improves precision, but it cannot remove a systematic bias. Accuracy is improved by calibration, not by repetition alone.
