Standards & glossary

The GUM/VIM nomenclature Open Gauge uses, and the standards its calibration engine implements.

Standards Open Gauge implements

Standard	Title	Relevance to Open Gauge
JCGM 100:2008 (GUM)	Guide to the expression of uncertainty in measurement	The foundational document behind the uncertainty budget — Type A/B evaluation, combination, expansion, coverage factors.
JCGM GUM-6:2020	Developing and using measurement models	The most directly applicable document to Open Gauge's calibration-coefficient data model — coefficient covariance, propagating uncertainty through a fitted curve.
ISO/IEC 17025:2017	General requirements for the competence of testing and calibration laboratories	§7.1.3/§7.8.6 require documenting a decision rule whenever a pass/fail statement is issued; §7.8.4.3 governs what a certificate may state about calibration intervals.
JCGM GUM-1:2023	Guide to the expression of uncertainty in measurement — Part 1: Introduction	A roadmap/overview of the reorganized GUM document suite.

Core nomenclature (GUM / VIM)

Open Gauge's UI, API field names, and certificate language use these terms precisely — they are not interchangeable synonyms.

Term	Symbol	Definition
Measurand	$Y$	The particular quantity subject to measurement.
Input quantities	$X_1, \ldots, X_N$	Quantities the measurand depends on: $Y = f(X_1, \ldots, X_N)$ .
Output estimate	$y$	The computed measurement result, $y = f(x_1, \ldots, x_N)$ .
Standard uncertainty	$u(x_i)$	Uncertainty of a result expressed as one standard deviation.
Type A evaluation	—	Uncertainty evaluated by statistical analysis of a series of observations (e.g. repeatability of calibration-point residuals).
Type B evaluation	—	Uncertainty evaluated by any other means: manufacturer specs, calibration certificates, handbook data, resolution, judgement. Type A/B is a classification of evaluation method, not of "random" vs. "systematic" error — GUM explicitly deprecates the term "systematic uncertainty."
Combined standard uncertainty	$u_c(y)$	Standard uncertainty of a result derived from several other quantities — the positive square root of a sum of variance/covariance terms weighted by sensitivity.
Expanded uncertainty	$U$	$U = k \cdot u_c(y)$ . Defines an interval expected to encompass a stated fraction of values reasonably attributable to the measurand.
Coverage factor	$k$	Numerical multiplier applied to $u_c(y)$ to obtain $U$ . Must always be stated alongside $U$ .
Sensitivity coefficient	$c_i = \partial f/\partial x_i$	Describes how $y$ varies with a small change in $x_i$ .
Degrees of freedom	$\nu$	Reliability indicator of a standard uncertainty estimate (e.g. $\nu = n-1$ for a mean of $n$ observations, $\nu = n-m$ for an $m$ -parameter least-squares fit).
Correlation coefficient	$r(x_i, x_j)$	$r = u(x_i, x_j) / [u(x_i)u(x_j)]$ , bounded $[-1, 1]$ .
Correction	—	A value added, or factor applied, to compensate a recognized systematic effect. GUM assumes all such corrections are applied before uncertainty evaluation.

Error is an idealized, unknowable quantity (result − true value). Uncertainty is a positive parameter characterizing the dispersion of values reasonably attributable to the measurand. Open Gauge's field names (max_error, combined_uncertainty, expanded_uncertainty) are chosen to be consistent with this distinction — max_error is an assessed error from real data, while the uncertainty fields describe the doubt around a result, not the result itself.

Standards Open Gauge implements

Core nomenclature (GUM / VIM)

Error ≠ Uncertainty

On this page