POTENTIAL EFFECTS OF BANDING AS A FUNCTION OF TEST RELIABILITY

Research output: Contribution to journalArticlepeer-review

Abstract

Cascio, Outtz, Zedeck, and Goldstein (1991) described the application of a number of test score banding procedures in personnel selection. Equations are developed illustrating the relationship between the width of test score bands and test reliability. When reliability is moderate to low, bands are likely to be larger than the standard deviation of the test, and are likely to include a large proportion of the applicant pool. The relationships between band widths and the differences between higher scoring and lower scoring groups are also examined. When the band is smaller than the differences between groups (which may happen when highly reliable tests are used), banding may not by itself prove effective as a means of reducing the adverse impact of tests, even when banding systems that maximize opportunities for members of the lower scoring group are used.

Original languageEnglish
Pages (from-to)477-495
Number of pages19
JournalPersonnel Psychology
Volume47
Issue number3
DOIs
Publication statusPublished - Sep 1994
Externally publishedYes

Fingerprint

Dive into the research topics of 'POTENTIAL EFFECTS OF BANDING AS A FUNCTION OF TEST RELIABILITY'. Together they form a unique fingerprint.

Cite this