ASME PTC 19.1:1998 pdf download Test Uncertainty
3.2 GLOSSARY
accuracy: the closeness of agreement between a mea-sured vaiue and the true vaiue.
calibration: the process of comparing the response ofan instrument to a standard instrument over somemeasurement range.
calibration hierarchy: the chain f calibrations whichinks or traces a measuring instrument to a primarystandard.
confidence ievel: the probability that the true valuefalls within the specified limits.
degrees of freedomm (v): a sammple of N vajues is saidto have N degrees of freedom, and the first statisticcalculated from it also is said to have N degrees offreedom. The degrees of freedom are reduced by. onefor each previously calculated statistic used to calcu-late a new statistic.
elemental error; the systematic or random error associ-ated with a single error source.
elermenlal uncerlainly: the systematic or random un-certainty associated with a single uncertainty source
estimnale: a value calculated from a sampie which isused to estimate the true value of an entire populationFor example, the sample standard deviation, S, is anestimate of the population standard deviation, o.influence coefficient: see sensitivity.
mcan (X): the arithmetic average of N readings
measurement error (8): the true, unknown differencebetween the measured value and the true value.
paramefer; a measured quantity, such as temperaturepressure, or stress, used in deriving a result. The definition differs from that used in statistics.
population: the set of all possible measurements of aparameter.
random error (e): sometimes called precision; the truerandom error which characterizes a member of a setof measurements. e varies in a randum, GaussianNormnai manner, from measurement to measurement
resu/t (R): a value calculated from a number of param-eters.
sample size (N): the number of individual measurements in a sample or used to calculate a mean.
sensitivity: the ratio of the change in a result to a unitchange in a parameter.
population standard deviation (o): a value whichquantifies the dispersion of a population.
standard crror of cstimatc (SEE): the measure of dispersion of the dependent variable about a least squaresregression or curve.
statistic: any numerical quantity dcrivcd from the sample data. X and S are statistics.
Student’s t: a value used herein to estimate the uncertainty for a given confidence level, obtained from tables entered with degrees of freedom at the chosenconfidence leve!.
systematic error (B): sometimes called bias; the truesystematic or fixed error which characterizes ever)member of any set of measurements from the population. The constant component of the total measurement error, 8.
systematic uncertainty (B): the 95% confidence levelestimate of the limits of a true systematic error, Boften determined by judgment.
traceability: the ability to trace the calibration of ameasuring device through a chain of calibrations toa primary standard. Traceability does not guaranteeaccuracy，it only indicates documented calibrationhicrarchy.
true value: the actua! value of the parameter beingmeasured.