Blackwell Reference Online

Extract

Boehm (1972) provided a definition of single‐group validity that distinguished it from differential validity . She explained that single‐group validity exists when (1) a predictor demonstrates validity that is statistically different from zero for one group but not another group, and (2) there is no statistically significant difference between the validities of two groups. Boehm (1972) argued that the occurrences of single‐group validity far outnumbered the instances of differential validity. However, Schmidt, Berner, and Hunter (1973) presented evidence that when differences in sample sizes are taken into account, there is little support for the single‐group validity argument. Furthermore, when the issue is taken to the population level, it becomes untenable. Two population validities cannot be equal and, at the same time, have one be equal to zero and another one not equal to zero. Thus, the usefulness of single‐group validity has been questioned. ( 1972 ). Negro–white differences in validity of employment and training selection procedures: Summary of research evidence . Journal of Applied Psychology , 56 , 33 – 9 . ( 1973 ). Racial differences in validity of employment tests: Reality or illusion . Journal of Applied Psychology , 58 , 5 – 9 . ... log in or subscribe to read full text