Premium
A S tatistical C orrection to 20 years of B anding
Author(s) -
Gasperson Sean M.,
Bowler Mark C.,
Wuensch Karl L.,
Bowler Jennifer L.
Publication year - 2013
Publication title -
international journal of selection and assessment
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.812
H-Index - 61
eISSN - 1468-2389
pISSN - 0965-075X
DOI - 10.1111/ijsa.12016
Subject(s) - sed , statistics , standard error , econometrics , test (biology) , psychology , mathematics , astrophysics , computer science , physics , ecology , biology , programming language
Statistically based banding is often considered a viable method for minimizing adverse impact in test‐based employment decisions. By utilizing the standard error of the difference ( SED ), scores are equated based on the assumption that there is substantial unreliability in any single observed score. However, based on the derivations of D udek, the formula commonly used to calculate the standard error of measurement ( SEM ) – a component that is typically used to calculate the SED – is incorrect. Specifically, utilizing the SEM when calculating the SED produces a band of observed scores around a true score, not a band of true scores around an observed score as would be appropriate for banding. This study compares the differences between banding‐based selection decisions when the appropriate SED formula – which utilizes the standard error of estimate – is and is not applied. Overall, results suggest that utilizing the appropriate formula for calculating the SED produces substantial variations in employment decisions. The potential legal and ethical implications of these discrepancies are discussed.