Personnel Selection with Top‐Score‐Referenced Banding: On the Inappropriateness of Current Procedures

Abstract

The method of selecting among job applicants using statistically based banding has been proposed over the last 10 years as a way to increase workforce diversity. The method continues to be reviewed by academics and considered by practitioners. Although the goal of increasing workforce diversity is important, statistical banding of scores remains controversial. We present a set of unique, statistically and theoretically based criticisms of a form of banding (top-score-referenced banding) that is widely used in hundreds of jobs in the public sector throughout the United States. We suggest that even within the premises of such banding, the wrong formula is used to estimate the standard error of measurement and standard error of the difference. One consequence is that too many individuals are labeled as essentially equal with respect to test scores. A related consequence is that test scores within a single band are statistically different and should therefore be treated as such for selection purposes. A more logically and statistically defensible procedure for responding to diversity concerns is to continue to attend to adverse impact issues at each step of the recruiting and test development process.

Banding Selection Scores in Human Resource Management Decisions: Current Inaccuracies and the Effect of Conditional Standard Errors

“…To understand our analysis, it is important to again note that banding theorists have emphasized that bands should be computed based on the top score of the available distribution as the referent point. We have shown that if the focus is on the top score, then conditional standard errors are particularly appropriate (see Bobko & Roth, 2004, for other implications of such a focus on the top score). As such, use of bands formed using the typical CTT-based SEM from Equation 1 (which assumes homogenous standard errors) is not appropriate.…”

No Steps Forward, Two Steps Back: The Fallacy of Trying to “Eradicate” Adverse Impact?

“…Lindsey et al suggest that banding may be an effective approach to the “reduction of subgroup differences.” Unfortunately, however, the consensus in the extant literature is that the effectiveness of banding as an adverse impact reduction technique is dependent on basing the selection out of bands on the protected class status variable of interest (Barrett, Doverspike, & Arthur, ; Bobko & Roth, ), a practice that is in violation of Section 106 of CRA 1991. Furthermore, contrary to Lindsey et al's statement, banding is an adverse impact reduction technique not a subgroup difference reduction technique (Arthur et al, ).…”

A Statistical Correction to 20 years of Banding

“…By this standard, the highest and lowest scores in the range receive the same grade (e.g., both a 100% and a 90% receive an ‘A’). However, as noted Bobko and Roth (), these groupings ‘are an administrative convenience only; they are not necessarily justified on statistical and psychometric bases’ (p. 292). Yet these assignments are commonly accepted without reservation.…”