Sampling experiments were used to assess the Type I error rates of the t test in situations where classes were randomly assigned to groups but analyses were carried out on individual student scores. Even small amounts of between-class variation caused large inflations in the Type I error rate of the t test. (Author/BW)

This paper compares an uncorrected with a corrected correlation between a selection test and a test-criterion in terms of expected mean square error (EMSE). It presents evidence that although the uncorrected may be more biased than the corrected correlation, it may have a smaller EMSE value, especially in small samples. (Author/PN)

Data for four-, five-, and seven-position Likert formats from 292 undergraduates showed systematic error varied among formats, i.e., central tendency errors tended to increase with increasing number of categories and to reduce variances expected. (Author)

A model which gives maximum likelihood estimates of measurement error within the context of a simplex model for practice effects is presented. The appropriateness of the model is tested for five traits, and error estimates are compared to the classical formula estimates. (Author/JKS)

Results of an eight-hour training program designed to minimize rating errors supported the hypothesis that low correlations were a result of rating errors made by supervisors. Of the five predictors, four correlated significantly with the performance ratings that were conducted after the supervisors had received the training. (Author)

This paper presents a scientific rationale for deciding the number of points to use on a grading scale in any given assessment situation. The rationale is applied to two common methods of assessment (multiple-choice and essay tests) and an example of a composite assessment. (Author/SJL)

Sattler's standard deviation technique for interpreting strengths and weaknesses on the Stanford-Binet Intelligence Scale has been simplified by Kaufman and Waterstreet in the form of an easy-to-use table. A refinement of their table is presented, with an example to demonstrate its use. (Author/CTM)

Salient concerns for practitioners of fitness testing are identified. (JD)

Describes study results that compared different ways of measuring frequency of alcohol use employed in previous research. Results of intake interviews with clients (N=832) indicate that frequency-of-alcohol-use reports can be affected by the type of response options used and by the location of items in a self-administered microcomputer interview.…

Eighty-seven normal older people were administered the Wisconsin Sorting Test on two occasions averaging over a year apart. There were average retest gains of 5 to 7 standard score points. The standard error of prediction, standard error of difference, and abnormal test-retest discrepancy scores were calculated for clinical use. (SLD)

Due to inaccuracies in method, public libraries consistently undermeasure their reference transactions. This article chronicles the process of developing ways to systematize the count. Results of a literature survey, merits of various sample sizes, sample selection, and calculations are all discussed. Appendices include a list of categories of…

This overview of the role of error and tolerance for error in measurement asserts that the generic precision associated with a measurement procedure is defined as the root mean square error, or standard error, in some relevant population. This view of precision is explored in several applications of measurement. (SLD)

Use of the Mantel-Haenszel procedure as a test for differential item functioning under the Rasch model of item-response theory is examined. Results of the procedure cannot be generalized to the class of items for which item-response functions are monotonic and local independence holds. (TJH)

Recently, C. E. McCulloch (1987) suggested a modification of the Morgan-Pitman test for comparing the variances of two dependent groups. This paper demonstrates that there are situations where the procedure is not robust. A subsample approach, similar to the Box-Scheffe test, and the Sandvik-Olsson procedure are also assessed. (TJH)

Aggregate scoring was applied to a recertifying examination for medical professionals to generate an answer key and allow comparison of peer examinees. Results for 1,927 candidates for recertification indicate considerable agreement between the traditional answer key and the aggregate answer key. (TJH)