Hoyt's analysis of variance procedure for estimating reliability assumes that the residual mean square estimates error variability. If, however, an individual's true score varies across items, it is argued that residual mean square estimates two components--error and interaction--and hence Winer's modification of Hoyt's formula, understimates the…

Two procedures for the display of item analysis statistics are described. One procedure allows for investigation of difficulty; the second plots item difficulty against item discrimination. (Author/JKS)

A procedure for estimating the reliability of a factorially complex composite is considered. An application of its use with Scholastic Aptitude Test data is provided. (Author/JKS)

A computer program providing comprehensive test and item analysis is presented. Completing its performance on one run, the program, written in Fortran and emphasizing ease of use, integrates various statistical techniques for analyzing individual items and the overall test, in addition to generating a variety of standard scores. (Author/JKS)

The interaction of subjects with test items is investigated. It is suggested that psychometricians rely too heavily on inferences about the nature of the interaction. An approach to data analysis is proposed which is more directly related to this interaction. (JKS)

The factor structure of scores on the Adult Manifest Anxiety Scale-College Version (AMAS-C), a new self-report measure of chronic, manifest anxiety, is examined across gender for a sample of 943 college students (608 women and 335 men). Values for the coefficient of congruence and salient variable similarity index are calculated between each of…

Results of discriminant analysis are of restricted value in the counseling setting because discriminant functions often lack psychological interpretability. A technique is proposed for obtaining rotated discriminant function scores which should have the same clarity of meaning as rotated factors from factor analyses. (Author/JKS)

The Guttman scale is discussed from the viewpoint of errors in response patterns. The errors are assumed to be distributed as a binomial. A double-barreled significance test is suggested having two probabilities: high probability and low probability. (Author)

Six methods of scoring multiple true-false items were compared in terms of reliabilities, difficulties, and discrimination. Results suggest that, for norm-referenced score interpretations, there is insufficient evidence to support any one of the methods as superior. For criterion-referenced score interpretations, effects of scoring method must be…

Cognitive differences between 987 LD children and 178 EH children in public schools on a psychoeducational assessment battery were studied, and differences in factor structure were investigated. Caution is suggested in interpreting the results of multivariate statistical analyses, which indicated heterogeneity in the matrices of LD and EH…