Use of small-sample-based reference limits on a group basis

Abstract

The evaluation of a biochemical or hematological quantity measured in a study group of employees during occupational health assessments involves a comparison with a reference sample group. Part of this evaluation consists of checking whether the percentage of values larger than a predetermined upper reference limit is significantly larger than the percentage normally expected (2.5%, if the 97.5 percentile is used as the upper reference limit). The reference limit, however, is estimated from a random reference sample, the size of which, for many reasons, may be relatively small; as a consequence, the reference limit estimate will be imprecise. In situations in which the reference sample size is smaller than or not much larger than the study sample size, this imprecision results in the usual binomial test of significance being highly inappropriate. We provide an exact nonparametric test valid for all reference sample sizes.