The following table provides critical values for $$G(\alpha, n)$$, where $$\alpha$$ is the probability of incorrectly rejecting the suspected outlier and n is the number of samples in the data set. There are several versions of Grubb’s Test, each of which calculates a value for Gij where i is the number of suspected outliers on one end of the data set and j is the number of suspected outliers on the opposite end of the data set. The critical values for G given here are for a single outlier, G10, where
$G_\text{exp} = G_{10} = \frac {|X_{out} - \overline{X}|} {s} \nonumber$
The suspected outlier is rejected if Gexp is greater than $$G(\alpha, n)$$.
 $$\frac {\alpha \ce{->}} {n \ce{ v }}$$ 0.05 0.01 3 1.155 1.155 4 1.481 1.496 5 1.715 1.764 6 1.887 1.973 7 2.202 2.139 8 2.126 2.274 9 2.215 2.387 10 2.29 2.482 11 2.355 2.564 12 2.412 2.636 13 2.462 2.699 14 2.507 2.755 15 2.549 2.755