Abstract
The predictive validity of the Stanford Mathematics Test was examined across race and sex. This investigation included 426 students equally divided between black and white students in two separate cohorts. The Stanford Mathematics Test (Intermediate II) was administered in the sixth grade and the Stanford Mathematics Test (Advanced) was administered in the eighth grade. The criterion was the California Achievement Test (Mathematics) given to one cohort in the eighth grade and to the other cohort in the ninth grade. Regression equations were employed to predict criterion performance and residuals were calculated. Residuals were examined with analyses of variance. No significant differences were found in mean residuals by race. Differences of small magnitude occurred by sex in one cohort which indicated underprediction for females and overprediction for males.
Get full access to this article
View all access options for this article.
