In response to growing concern about the lack of basic writing skills, this paper presents an overview of the issues involved in selecting a method for the assessment of students' writing skills. After general criteria for determining the appropriateness of a writing evaluation procedure are outlined, the merits and limitations of objective tests…

Three techniques for estimating Kuder Richardson reliability (KR20) coefficients for incomplete data are contrasted. The methods are: (1) Henderson's Method 1 (analysis of variance, or ANOVA); (2) Henderson's Method 3 (FITCO); and (3) Koch's method of symmetric sums (SYSUM). A Monte Carlo simulation was used to assess the precision of the three…

Explores the usefulness of a short version of the Minnesota Multiphasic Personality Inventory (Mini-Mult) in a university counseling center as well as determines whether earlier results of investigations of the Mini-Mult could be replicated with a sample of college males and females demonstrating no gross abnormalities. (RC)

An upper-asymptote parameter was added to the three-parameter logistic item response model. This four-parameter model was compared to the three-parameter model on four data sets. The fourth parameter increased the likelihood in only two of the four sets. Ability estimates for the students were generally unchanged by the introduction of the fourth…

The problem that this research addressed was one of decision making. Given three sets of criterion-referenced tests which were designed to be parallel in content, would a traditional reliability coefficient produce different decisions about the reliability of those tests than would kappa? The procedure used collected statewide results on 136 test…

Results of a comparative study of F and Q tests, in a randomized block design with one replication per cell, are presented. In addition to these two procedures, a multivariate test was also considered. The model and test statistics, data generation and parameter selection, results, summary and conclusions are presented. Ten tables contain the…

Differences in design between norm referenced measures (NRM) and criterion referenced measures (CRM) are reviewed, and some of the procedures proposed on designing and evaluating CRM are examined. Differences in design of NRM and CRM are said to arise from the different purposes that underlie each measure. In addition, there are differences among…

This study compared a domain referenced approach with a traditional psychometric approach in the construction of a test. Results of the December, 1975 Quarterly Profile Exam (QPE) administered to 400 examinees at a university were the source of data. The 400 item QPE is a five alternative multiple choice test of information a "safe"…

Freshmen (N=202) took two batteries of aptitude tests 10 months apart. Six pairs of tests were studied. Two pairs were identical, two were parallel, and two were completely different. This design made it possible to separate three components of practice: (a) general test sophistication, (b) specific practice effect, and (c) item familiarization.…

It was found that the General Cognitive Index scores of the McCarthy Scales correlated well with the Stanford-Binet IQ scores. However, 40 of the 44 subjects scored higher on the Stanford-Binet than on the McCarthy Scales. (Author)

Fabricated test protocols were used to study how effectively examiners agree in scoring ambiguous WISC-R responses. The results suggest that, even with the improved WISC-R manual, scoring remains a difficult and challenging task. (Author)

Three algorithms for selecting a subset of originally available items, to maximize coefficient alpha, were compared on the size of the resulting alpha and computation time required with nine sets of data. The characteristics of a computer program to perform these item analyses are described. (Author/JKS)

This study investigates the usefulness of the Preschool Attainment Record (PAR) as a measure of children's developmental skills. The PAR was compared to the Denver Developmental Screening Test (DDST) as the criterion measure, and they were found to correlate .891. (Author)

Changing from the SVIB to the SCII increased the probability of machine-scoring errors. This study examined the accuracy and consistency of SCII profile scores for three commercial scoring agencies. Results indicated improved performance compared with previous studies and suggested that scoring errors should be minimal for the SCII. (Author)