Optimizing test performance of moderately and severely mentally retarded adolescents and adults.

This study provided further evidence for the validity of a learning potential assessment procedure with institutionalized moderately and severely retarded adolescents and adults. Significant positive correlations were obtained between psychometric and learning scores, attendants' and teachers' ratings of ability, and the posttraining scores on the modified Kohs Extended Learning Potential procedure. In addition, performance on this test-train-test procedure was compared with a train-within-test format for two different tasks: training embedded within the administration of the Leiter International Performance Scale and a formboard version of Raven's Coloured Progressive Matrices. The students responded equally to the two formats. Stanford-Binet IQs were least predictive of performance on the three learning potential measures and were unrelated to teachers' and attendants' ratings of ability. The implications of these data were discussed with particular attention to the potential advantages of the train-within-test model.