Three versions of a probabilistic model adapted from the theory of information retrieval--a binary version, a version using the full value of the data, and a version using principal components--were tested and applied to data available from application forms to predict graduate school performance of library school students. (EM)

Argues that perception studies and ranking are lacking in validity and reliability because of small sample size, simplistic statistical analyses, and the evaluation of quality by educators. It is asserted that quality control is more valid when evaluated by the customers of education, i.e., the students. (11 references) (EA)