A scale was developed for judging the relative value of various media in teaching children. Posttest scores were partitioned into several components: error, prior knowledge, guessing, and gain from the learning exercise. By estimating the amounts of prior knowledge, guessing, and error, and then subtracting these from the total score, an index of…

This bibliography is a list of theoretical and empirical studies of the Rasch One Parameter Logistic Measurement Model. A total of 96 entries are included. (KM)

The stability of various item discrimination indices when a particular item assumes membership within different sets of items was investigated. Results suggest that when item discrimination is used as a significant factor in determing which items from several forms will be selected for inclusion in a test, the actual items selected are less a…

A discussion of criterion-referenced measures is presented. Two characteristics define the criterion-referenced measure: the presence of a performance criterion, and test items keyed to a set of behavioral objectives. The performance criterion, in an educational setting, is usually a relative standard of performance. There are two ways of…

Using ordering theory, a boolean algebraic measurement model in which item response patterns are viewed as atoms in a boolean algebra with as many generators as there are items being considered, a hierarchy-generative procedure is developed. This procedure relates to the determination of prerequisite relationships between pairs of items. An…

Content validity is concerned with three components: (1) the job content; (2) the test content, and (3) the strength of the relationship between the two. A content validation study, to be considered adequate and defensible should include at least the following four procedures: (1) A thorough and accurate job analysis (to define the job content);…

One of the most important contentions of the Rasch model of item analysis is that two tests of the same trait, having some items in common, can be linked together using a "linking constant" derived from the common items. This would be accomplished by administering both tests to a sample of testees, calibrating the items of the tests…

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)

The validity of five methods of estimating the reliability of criterion-referenced tests was evaluated across nine conditions of variability among item means. The results were analyzed by analysis of variance, the Newman-Keuls test, and a nonparametric procedure. There was a tendency for all of the methods to be conservative. (Author/JKS)

Examines the Personal Health Survey methodology and suggests that in studying the factorial composition of physical and mental health complaints in limited populations, the data provides normative information "only" for the samples tested on one occasion. States further that it would require large-scale normative studies to make any…

Latent partition analysis is shown to be useful in determining the conceptual homogeneity of an item population. Such item populations are useful for mastery testing. Applications of latent partition analysis in assessing content validity are suggested. (Author/JKS)

This research simulated responses of 75 subjects to 30 items under the Birnbaum model and attempted a fit to the data using the Rasch model. When item discriminations varied from a variance of .05 to .25, there was only a slight increase in lack of fit as the variances increased. (Author/CTM)

Investigates empirically, for a sample of university examinations in engineering, the influence of examination length on reliability and discrimination. (Author)

Measures of consistency and completeness of order relationships derived from test data such as Guttman scales are proposed. The measures are generalized to apply to incomplete data such as data from tailored testing. (Author/JKS)

Urry's procedure for approximating latent trait test models is shown to tend to underestimate item discriminatory power and overestimate item difficulty. A method for correcting these biases is provided, and implications of the procedures are discussed. (Author/JKS)