Generalizability theory was used to analyze the dependability of elementary school student ratings of attitudes toward school subjects. The rating scales under investigation have been developed to measure the attitudes of students toward four school subjects at both the primary and intermediate levels. Two generalizability coefficients, differing in assumptions of true and error variance, were calculated which estimated the dependability of assessing class attitude. A third coefficient was calculated which estimated the dependability of assessing individual student attitudes. The effects of varying the number of scale items and/or students on the dependability of class means or individual student attitudes were investigated. The results suggest the attitude scales measuring primary student attitudes toward school subjects are not dependable indicators of student attitudes when class is the unit of analysis. There is cogent evidence that both primary and intermediate student attitudes can be dependably evaluated by the attitude scales when the student is the unit of analysis. (Author)