Accuracy and precision are used in context of measurement. Accuracy refers to the degree of conformity and correctness of something when compared to a true or absolute value, while precision refers to a state of strict exactness — how consistently something is strictly exact.

In other words, the precision of an experiment, object, or value is a measure of the reliability and consistency. The accuracy of an experiment, object, or value is a measurement of how closely results agree with the true or accepted value.

Both accuracy and precision are terms used in the fields of science, engineering, and statistics.

## Comparison chart

Accuracy versus Precision comparison chart
AccuracyPrecision
Definition The degree of conformity and correctness of something when compared to a true or absolute value. A state of strict exactness — how often something is strictly exact.
Measurements Single factor or measurement Multiple measurements or factors are needed
Relationship Something can be accurate on occasion as a fluke. For something to be consistently and reliably accurate, it must also be precise. Results can be precise without being accurate. Alternatively, results can be precise AND accurate.
Uses Physics, chemistry, engineering, statistics, and so on. Physics, chemistry, engineering, statistics, and so on.

## Defining Accuracy and Precision

In his review of Simon Winchester's The Perfectionists: How Precision Engineers Created the Modern World, James Gleick writes for the New York Review of Books

... precision involves an ideal of meticulousness and consistency, while accuracy implies real-world truth. When a sharpshooter fires at a target, if the bullets strike close together—clustered, rather than spread out—that is precise shooting. But the shots are only accurate if they hit the bull’s eye. A clock is precise when it marks the seconds exactly and unvaryingly but may still be inaccurate if it shows the wrong time.

## Examples

A measurement may be accurate but not precise, precise but not accurate, or neither, or both.

An example of bad precision with good accuracy might be a lab refrigerator that holds a constant temperature of 38.0F. A temperature sensor is tested 10 times in the refrigerator. The temperatures from the test yield the temperatures of: 37.8, 38.3, 38.1, 38.0, 37.6, 38.2, 38.0, 38.0, 37.4, 38.3. This distribution shows no impressive tendency toward a particular value (lack of precision) but each value does come close to the actual temperature (high accuracy).

Another example is the Antikythera mechanism, an ancient Greek analog computer that was used to predict astronomical positions and eclipses. It had 37 gear wheels and could follow the movements of the moon, including the irregular orbit of the moon where the moon’s velocity is higher in its perigee than in its apogee. The device was reasonably precise but not very accurate.

## Target Comparison

Accuracy is the degree of correctness, while precision is how strict that correctness is (or isn't) — how reproducible results are. For this example, consider results from a round of target practice.

Arrows are fired at a target, and measurements are taken in relation to the bull's eye at the center of the target. Accuracy describes how close the arrows are to the bull's-eye. The closer an arrow is to the bull's eye, the more accurate the shot.

How precise the shots are depends on how often the arrows land near each other on the target. When all or most arrows are grouped tightly together, the shots fired can be considered precise since they all landed near the same spot, if not necessarily near the bull's-eye. This is how results can indicate precision but not necessarily accuracy. However, it is important to note that it is not possible to reliably achieve accuracy without precision.

The target at left displays neither accuracy nor precision, while the target in the middle displays some precision but little accuracy. Finally, the third target, at right, shows both accuracy and precision.
Another picture showing the difference between accuracy and precision using the target-shooting metaphor. (a) is neither accurate nor precise because the shots are not close to the bull's-eye but all over the place. (b) is both accurate and precise. (c) is precise because the shots are clustered together, but not accurate because they are not close to the target.

## Number of Measurements

Accuracy can be improved by taking repeat measurements and taking an average. (This assumes that errors are randomly above and below the true value to the same degree). Therefore an experiment with a low degree of precision can provide accurate values where appropriate statics are applied.

Conversely, precision cannot be improved by taking repeated measurements but it is impossible to quantify precision without experimental repeats.

The danger when evaluating an experiment is that some errors are not random. In this case, an experiment could yield inaccurate results yet be highly precise.

## Quality

While a precise measurement may speak highly of an instrument's quality, an accurate reading will not reflect on the quality. Accuracy is an agreement of a measured value with an expected value. For example, a stopped clock will be accurate twice in day, but it will not be precise — i.e., able to consistently and accurately keep time throughout the day. In the case of a clock, how precisely it measures time matters a great deal and determines quality.