A method was developed for identifying students who may be at high risk for failing the State Board Licensing Examination (SBE) for registered nurses. The subjects used in developing prediction equations included 50 students who graduated from the nursing program at Saint Joseph's College (SJC) in North Windham (Maine) during the years 1983-84. The validation group included 105 students who graduated from the nursing program at SJC during the years 1985-88. Subjects were predominately single, white, females in their early twenties. The SBE score was the outcome variable. Predictor variables included subjects' Scholastic Aptitude Test (SAT) scores and college course grades in the areas of science, statistics, and nursing theory. Grade point averages were also used. Two standardized tests of nursing content--the National League for Nursing (NLN) test on Nursing of Children and the Mosby Assess Test (MAT)--were administered to the subjects. Prediction equations were developed from a step-wise regression analysis for each of the following periods: pre-admission; end of the freshman, sophomore, and junior years; and the end of the fall semester of the senior year. The verbal SAT score was the best predictor of failure in the freshman year, but it was replaced as the best predictor at the end of the sophomore year by the cumulative average of nursing and science course grades. The MAT was the best predictor in the senior year. The results support the predictive value of comprehensive tests that are similar in style and format to the SBE. Relationships exist between various test scores and SBE performance. It is concluded that pre-admission test scores, such as the verbal SAT, are valuable predictors early in a program. NLN examinations in the content area of maternal-child health are consistent predictors of SBE. (RLC)