Estimation of premorbid abilities remains an integral part of neuropsycholo
gical evaluations. Several methods of indirect estimation have been suggest
ed in the literature. Many of these methods are based in prediction via lin
ear regression. Unfortunately, linear regression has the well-reported tend
ency to underpredict high IQ scores and overpredict low IQ scores. This can
be shown to be an unavoidable statistical artifact of linear regression. W
e demonstrate a procedure to estimate premorbid IQ without the regression a
rtifact. The procedure has two steps: confirmation of construct equivalence
and psychometric equating. An example using real data is presented which s
hows the regression to the mean problem with prediction and compares it to
the results from equating. (C) 2001 National Academy of Neuropsychology. Pu
blished by Elsevier Science Ltd.