Validity of regression-based norms: An empirical test of the comprehensivenorms with older adults

This study empirically tested Fastenau and Adams' (1996) concerns about usi ng regression-based norms (RBN) to statistically correct for demographic in fluences. A widely used RBN system (Heaton, Grant, & Matthews, 1991) was ap plied to scores from 63 healthy older adults for the Trail Making Test, Bos ton Naming Test, and Wisconsin Card Sorting Test (WCST). Age influences on all tests were virtually eliminated by the RBNs, whereas education influenc es were created by the RBN (better educated older adults penalized by the n orms). Using RBNs from the Revised WCST Manual also created distortions, fa r overcorrecting for age. These findings cast considerable suspicion on nor ms that are generated by statistical regression when there are not adequate numbers of people supporting each demographic cell. Clinically, these norm s can lead to higher rates of false negatives (or missed diagnoses) in olde r adults, especially those with less education and especially women in thei r 60s.