Six different methods of computing factor scores were investigated in a sim
ulation study. Population scores created from oblique factor patterns selec
ted from the psychological literature served as the bases for the simulatio
ns, and the stability of the different methods was assessed through cross-v
alidation in a subject-sampling model. Results from 5 evaluative criteria i
ndicated that a simplified, unit-weighting procedure based on the factor sc
ore coefficients was generally superior to several unit-weighting procedure
s based on the pattern or structure coefficients. This simplified method of
computing factor scores also compared favorably with an exact-weighting sc
heme based on the full factor score coefficient matrix. Results are discuss
ed with regard to their potential impact on current practice, and several r
ecommendations are offered.