N-x rules are violated when there are 7, 8, 9, 10, or 12 control results on the same side of the mean.
Each of these rules has two applications:
Violations within a control level indicate systematic bias in a single area of the method curve.
Violations across control levels indicate systematic error over a broader range of concentrations.
The 7-x control rule is far more sensitive to analytical bias than the 12-x rule. The chance of finding seven consecutive control observations on one side of the mean is much higher than finding twelve.
The following figures show a Levey-Jennings Chart with data points violating the 8-x rule within a run and the 9-x rule across a run.
In This Section |
See Also |