Effects of verbally labeled anchor points on the distributional parameters of rating measures

Abstract

The hypothesis was examined that the negative skew found in most distributions of performance ratings is a function of the verbal labels used as anchors. When verbal labels quantified on the basis of the range of real-life performance were employed, distributional parameters (means, skewness) were affected. Typically used sets of labels were shown to be more negative than believed, thus tending to force responses toward the high end of the scale and thereby contributing to negative skew.