A Bayesian Model II approach to the estimation of proportions in m groups is extended to obtain posterior marginal distributions for the proportions. The approach is extended to allow greater use of prior information than previously and the specification of this prior information is discussed. (Author/RC)

The expected reliability of a multiple choice test is maximized by the use of three alternative items. (Author)

Many conservation studies have been performed using time consuming individual testing. The sequential studies reported in this paper describe the development of a group film test of conservation. (Author)

The results show that the delay-retention effect occurs under conditions approximating those of real instruction and confirm the interference-perseveration interpretation of the phenomenon. (Author)

Four different extensions to McNemar's problem concerning the hypothesis of equal probabilities for the unlike pairs of correlated binary variables are considered, each for testing simultaneous equality of proportions of unlike pairs in c independent populations of correlated binary variables, but each under different assumptions and/or additional…

A method of applying the discriminant function to correlated samples was discussed for the researcher interested in utilizing multivariate statistics to pre-post data. By finding the linear combination that maximizes differences in the groups, the t-statistic can be computed for correlated samples. (Author)

The educational and statistical validity of grading schemes is often open to question when multiple evaluation techniques are used. A method of scaling is proposed and discussed in relation to normal scores. (SD)

Studies the role that interactions play in predicting academic performance of kindergarten children who were follow studied into the first grade. (Author/DEP)

Supported by research grants MH-07003 and MH-11521 from the National Institute of Mental Health, U.S. Public Health Service.