Every measurement is affected by limitations arising from instruments, measurement procedures, environmental conditions, reference standards, and the definition of the quantity being measured. Measurement uncertainty expresses the dispersion of values that could reasonably be attributed to the measurand. It is not identical to measurement error. Measurement error is the difference between a measured value and a reference value, whereas uncertainty characterizes the doubt associated with the measurement result. The true value is generally not known exactly, so the error may not be directly determined. Standard uncertainty, represented by u, is expressed as a standard deviation. Type A evaluation uses statistical analysis of repeated observations, while Type B evaluation uses other information such as calibration certificates, instrument specifications, previous measurements, or scientific knowledge. Combined standard uncertainty, u_c, accounts for multiple uncertainty contributions and their correlations. For independent input quantities, uncertainty propagation often uses sensitivity coefficients and a root-sum-of-squares combination. Expanded uncertainty, U, is obtained by multiplying combined standard uncertainty by a coverage factor k. The reported result may be written as y = 12.34 ± 0.05 units, but the meaning of the uncertainty and the coverage factor should be explained. Relative uncertainty is the ratio of standard uncertainty to the absolute value of the measured quantity. Percentage uncertainty expresses this ratio as a percentage. When measurements are repeated, the sample mean and sample standard deviation provide estimates of the central value and spread. The standard uncertainty of the mean is commonly estimated by s/√n for independent observations under suitable assumptions. Systematic effects and random variation should be evaluated separately where possible. Calibration, traceability, uncertainty budgets, and appropriate statistical models are essential for reliable scientific measurement.
Measurement Uncertainty and Error Representation Symbols
Explains the symbols and conventions used to describe measurement uncertainty, measurement error, uncertainty intervals, standard uncertainty, expanded uncertainty, and statistical variation. It distinguishes uncertainty from error and introduces the notation used in scientific measurement reports.
uᵣ(y) = u(y)/|y|; U = k·u_c(y); u_c(y) = √(Σuᵢ²) for independent additive contributions with unit sensitivity coefficients
Explanation
Variables
| Symbol | Meaning | Unit |
|---|---|---|
y | Measurement result or estimate of the measurand | Same as the measured quantity |
u(y) | Standard uncertainty of the measurement result | Same as y |
uᵣ(y) | Relative standard uncertainty | Dimensionless |
u_c(y) | Combined standard uncertainty | Same as y |
U | Expanded uncertainty | Same as y |
k | Coverage factor used to obtain expanded uncertainty | Dimensionless |
n | Number of independent observations | Dimensionless count |
s | Sample standard deviation | Same as the observations |
Example or application
A worked example has not yet been added.
Definition
Measurement uncertainty is a non-negative parameter associated with a measurement result that characterizes the dispersion of values that could reasonably be attributed to the measured quantity.
Purpose
Provides a standardized framework for evaluating and reporting the reliability of measurements, combining uncertainty contributions, and comparing experimental results.
Importance
Uncertainty representation prevents measurements from being interpreted as exact when they are not. It supports reproducibility, calibration, scientific decision-making, quality assurance, and the evaluation of whether observed differences are meaningful.
Essential Symbols
| Symbol | Meaning |
|---|---|
u | Standard uncertainty. |
uA | Standard uncertainty evaluated by Type A statistical methods. |
uB | Standard uncertainty evaluated by Type B methods. |
u_c | Combined standard uncertainty. |
U | Expanded uncertainty. |
k | Coverage factor. |
Δ | Difference or change in a quantity; its precise meaning depends on context. |
ε | May represent relative error or another small parameter, depending on the field; it is not a universal uncertainty symbol. |
Uncertainty Types
| Type | Notation | Description |
|---|---|---|
Type A evaluation | uA | Evaluated using statistical analysis of a series of observations. |
Type B evaluation | uB | Evaluated using information other than the statistical analysis of repeated observations, such as certificates, specifications, or prior knowledge. |
Combined standard uncertainty | u_c | Calculated by combining the standard uncertainty contributions associated with the measurement model. |
Expanded uncertainty | U | Combined standard uncertainty multiplied by a coverage factor. |
Uncertainty Propagation
Independent Additive Contributions
u_c = √(u₁² + u₂² + ... + uₙ²)
General Measurement Model
y = f(x₁, x₂, ..., xₙ)
Uncorrelated Input Approximation
u_c²(y) = Σ[(∂f/∂xᵢ)²u²(xᵢ)]
Correlated Input Form
u_c²(y) = ΣᵢΣⱼ(∂f/∂xᵢ)(∂f/∂xⱼ)u(xᵢ,xⱼ)
Coverage
U = k·u_c(y)
Qualification
The simplified root-sum-of-squares expression applies only when the relevant contributions are independent and have unit sensitivity coefficients. The general measurement model must account for sensitivity coefficients and correlations.
Error And Uncertainty Distinction
| Concept | Symbol | Meaning |
|---|---|---|
Measurement error | e | Difference between a measured value and a reference value, often written e = measured value − reference value. |
Measurement uncertainty | u | Parameter characterizing the dispersion of values reasonably attributable to the measurand. |
Random error | Context-dependent | A component of measurement error that varies unpredictably across repeated measurements. |
Systematic error | Context-dependent | A component of measurement error that remains constant or varies predictably under specified conditions. |
Worked Examples
| Problem | Solution |
|---|---|
A measurement is 10.0 cm with standard uncertainty 0.2 cm. Calculate relative and percentage uncertainty. | uᵣ = 0.2/10.0 = 0.02. Percentage uncertainty = 0.02 × 100% = 2%. |
Two independent uncertainty contributions are 0.3 mm and 0.4 mm. Find their combined standard uncertainty when both have unit sensitivity coefficients. | u_c = √(0.3² + 0.4²) mm = 0.5 mm. |
A combined standard uncertainty is 0.02 kg and the coverage factor is 2. Find expanded uncertainty. | U = 2 × 0.02 kg = 0.04 kg. |
Five repeated measurements have a sample standard deviation of 0.10 s. Estimate the standard uncertainty of the mean. | u(mean) = s/√n = 0.10/√5 ≈ 0.0447 s, assuming independent observations and suitable statistical conditions. |
Reporting Conventions
Report a measurement result together with its uncertainty and unit.
Specify whether the uncertainty is standard or expanded.
State the coverage factor when expanded uncertainty is reported.
Avoid reporting more digits than the uncertainty and measurement process justify.
Explain whether the uncertainty represents a standard deviation, confidence interval, or another interval interpretation.
Use consistent units for the measured value and its uncertainty.
Include relevant assumptions and significant correlations in an uncertainty evaluation.
Common Errors
Treating uncertainty as identical to measurement error.
Adding independent standard uncertainties directly instead of combining them according to the measurement model.
Reporting expanded uncertainty without stating the coverage factor.
Ignoring correlations between input quantities.
Confusing instrument resolution with total measurement uncertainty.
Assuming that a coverage factor of 2 always guarantees exactly 95% coverage.
Applications
Laboratory measurement reporting.
Calibration and metrological traceability.
Quality control and industrial testing.
Scientific comparison of experimental results.
Physical constant measurements.
Environmental monitoring and analytical chemistry.
Reference
JCGM 100, Evaluation of Measurement Data: Guide to the Expression of Uncertainty in Measurement.
JCGM 200, International Vocabulary of Metrology (VIM).
NIST Technical Note 1297, Guidelines for Evaluating and Expressing the Uncertainty of NIST Measurement Results.
Related Topic
SCI-REF-006-101
SCI-REF-006-108
SCI-REF-006-109
SCI-REF-006-110
Sources and verification
Sources are shown as provided in the project data. Not every source has yet been independently verified. Please report errors or missing citations.
- Source verification pending; check an authoritative textbook, university, standards body, or peer-reviewed source.
Suggest a correction or source · More in Scientific Symbols & Notation