A new correction for controlling family-wise error rate in multiple comparison studies

Misleading conclusions can be drawn from multiple comparison studies if the critical p value is set as equivalent to the preselected statistical alpha level. This incorrect assumption is observed in many research publications where not enough attention was paid to the inflation of the critical p value as a result of increasing the number of comparisons. A new approach is proposed to control the false discovery rate for independent comparisons. The new approach renders more reliable critical p values and allows reducing the inflated values to the original preselected alpha level.