If more than one comparison among means is conducted at a given PCER, the EER will be higher than the PCER. The following inequality can be used to control the EER:

EER ≤ (c)(PCER)

where c is the number of comparisons performed. For example, if six comparisons are performed at the 0.05 significance level (PCER = 0.05), then the EER is less than or equal to (6)(0.05) = 0.30. If a researcher wishes to perform six comparisons and keep the EER at the 0.05 level, the 0.05/6 = 0.0083 significance level should be used for each comparison. That way, the EER would be less than or equal to (6)(.0083) = .05.

In general, to keep the EER at or below 0.05, the PCER should be:

PCER = 0.05/c where c is the number of comparisons.

More generally, to insure that the EER is less than or equal to α, use

PCER = α/c.

Adjusting the PCER in this manner is called either the "Bonferroni adjustment" or "Dunn's procedure" after the statisticians who developed it.