Guttman's assumption underlying his definition of "total images" is rejected. Partial images are not generally convergent everywhere. Even divergence everywhere is shown to be possible. The convergence type always found on partial images is convergence in quadratic mean; hence, total images are redefined as quadratic mean-limits.…

This paper develops theory and methods for the application of the Bayesian Model II method to the estimation of binomial proportions and demonstrates its application to educational data. (Author/RK)