An algorithm for updating the means of variances of a norm group after each computer-assisted administration of a test is described. The algorithm does not require storage of the whole data set, and provides for unlimited, continuous expansion of the test norms. (Author)

TESTER, a computer program which produces individualized objective tests from a pool of items, is described. Available in both PL/1 and FORTRAN, TESTER may be executed either interactively or in batch. (Author/JKS)

A computer/tape recorder interface was designed, which permits automatic oral adminstration of "true-false" or "multiple-choice" type tests. This paper describes the hardware and control program software, which were developed to implement the method on a DEC PDP 11 computer. (Author/JKS)

A computer program for analyzing and reporting the results of student rating scales designed to evaluate courses and instructors is described. It computes median ratings for the total scale, subscales, and items. Written in ANS FORTRAN, this program is compatible with most third generation machines. (Author/JKS)

MAPP (A Mathematics Placement Program) uses two COBOL programs to place entering freshmen in mathematics courses which are commensurate with their backgrounds and abilities. Having been used for three years, the program is considered to be a viable alternative to the traditional mathematics placement process. (Author/JKS)

This note described a FORTRAN IV, CDC, computer program for the canonical analysis of a two-way contingency table. (Author)

A computer program for estimation of trends in longitudinal research based on the moving average was presented and applied to a sample set of data. The program allows both standard and weighted procedures for supression of incidental variation. (Author/JKS)

A computer program for computing coefficients for nominal scales, such as the contingency coefficient, Cramer's V, and others is described. (Author/JKS)

Existing generalizations of the G Index of Agreement of two subjects on n dichotomous items are discussed and an alternative index for ordinal scales with fixed neutral points is proposed. The proposed index can be used as a normalized scalor product and for both item and person similarities. (JKS)

An analysis of variance procedure for testing differences in r-squared, the coefficient of determination, across independent samples is proposed and briefly discussed. The principal advantage of the procedure is to minimize Type I error for follow-up tests of pairwise differences. (Author/JKS)

Analysis of variance computed intraclass reliability coefficients are often underestimated because analysis of variance assumptions are ignored. Assumptions of an alternate technique are explored. Biasedness of the intraclass reliability coefficient is discussed and a table of correction presented. (Author)

Two statistics for use in the Shine-Bower single-subject analysis of variance designs are compared. Advantages and precautions concerning an alternate statistic to the mean square successive difference test for testing the slow change assumptions of the Shine-Bower error term are presented. (JKS)

The problem of bias in rankings due to the initial position of entities when presented to judges is discussed. A modification of the Friedman Two-Way Analysis of Variance to test "ranking error" is presented. (JKS)

Maximally reliable composites found in canonical reliability when expressed in the form of a canonical factor analysis solution are shown to have highly desirable data reduction properties. Theoretical relationships among canonical factor analysis, principal components analysis and canonical reliability analysis are emphasized. (Author/JKS)

A principal components analysis of matrices of Spearman's rho statistic for inter-rater reliability is proposed as an alternative to Kendall's coefficient of concordance. Advantages and possible uses of the proposed method are presented. (JKS)