A dependence between input estimates, quantified by a correlation coefficient from -1 to +1 or by their covariance, which arises when inputs share a common source such as the same reference standard, thermometer or calibration run. Full positive correlation makes contributions add linearly instead of by root sum of squares, while in a ratio or difference shared errors can cancel. Ignoring correlation can understate or overstate uncertainty by a large factor.
Both thermometers were calibrated against the same SPRT, so their corrections are correlated, put the covariance term in.
Also heard as
- correlation coefficient
Related terms
Law of propagation of uncertainty
The first-order formula that combines input standard uncertainties, weighted by sensitivity coefficients, into the output uncertainty.
RSS
Root sum of squares, combining independent uncertainty contributions by squaring, adding and taking the square root.
Combined standard uncertainty
The total standard uncertainty of a result, found by combining all input uncertainties through the measurement model.
Sensitivity coefficient
The factor that converts an input's uncertainty into its effect on the output, the partial derivative of the model.