Single administration (beta-binomial) estimates for the raw agreement index p and the corrected-for-chance kappa index in mastery testing are compared with those based on two test administrations in terms of estimation bias and sampling variability. Bias is about 2.5 percent for p and 10 percent for kappa. (Author/RL)

Five indices are discussed that should logically discriminate between situations in which: (1) the linear equating method (LEM) adequately adjusts for difference between score distributions of two approximately parallel test forms; or (2) a method more complex than the linear equating method is needed. (RL)

In this paper, a proposal is made by which a content validity coefficient can be calculated. An example of the use of the coefficient is given, demonstrating that different question combinations in a CSE biology examination in which a choice of questions was given gave different levels of content validity. (Author)

The paper documents experiments designed to compare essay and multiple-choice tests as means of testing science learning. Results indicate it is easier to score high on multiple-choice tests; some students substitute quantity on essay tests; and essay tests reveal weaknesses hidden by multiple-choice tests. (RE)

The computational difficulty of the word problem sections of eight standardized achievement tests was analyzed with respect to the variety of computational procedures and the number of digits per whole number computation. Analysis reveals considerable variation among the current tests in terms of computational procedure and difficulty. (Author/MK)

Investigates two evaluative hypotheses related to test item sequence and the performance of the students who take the tests. (SA)

A discussion of differential item functioning (DIF) in the context of attitude assessment is followed by examples involving the detection of DIF on an attitudes-toward-science scale completed by 1,550 elementary school students and the finding of no DIF in a workshop evaluation completed by 1,682 adults. (SLD)

Reviews and illustrates some of the current technological developments in computer-based testing, focusing on novel item formats and automated scoring methodologies. The review shows a number of innovations being researched and implemented. (SLD)

Compared three online pretest calibration scaling methods through simulation: (1) marginal maximum likelihood with one expectation maximization (EM) cycle (OEM) method; (2) marginal maximum likelihood with multiple EM cycles (MEM); and (3) M. Stocking's method B. MEM produced the smallest average total error in parameter estimation; OEM yielded…

Presents the results of an investigation about the effect of question order randomization on the psychometric properties of two frequently used oral and written apprehension instruments: McCroskey's oral communication apprehension scale and Daly and Miller's writing apprehension scale. Shows that the measurement properties of these instruments…

Describes a project used in a sophomore-level psychological testing and measurement course. Students worked through the different phases of developing a test focused on item writing, reliability, and validity. Responses from both students and instructors have been consistently positive. (MJP)

Some alternative criteria for item selection in adaptive testing are proposed that take into account uncertainty in the ability estimates. A simulation study shows that the likelihood weighted information criterion is a good alternative to the maximum information criterion. Another good alternative uses a Bayesian expected a posteriori estimator.…

An item selection procedure for computerized adaptive testing based on average global information is proposed. Results from simulation studies comparing the approach with the usual maximum item information item selection indicate that the new method leads to improvement in terms of bias and mean squared error reduction under many circumstances.…

Analyzed examinee responses to conventional (multiple-choice) and innovative item formats in a computer-based testing program for item response theory (IRT) information with the three parameter and graded response models. Results for more than 3,000 adult examines for 2 tests show that the innovative item types in this study provided more…

Studied the primacy effect (tendency to select items closer to the left side of the response scale) in Likert scales worded from "Strongly Disagree" to "Strongly Agree" and in the opposite direction. Findings for 386 high school and college students show no primacy effect, although negatively worded stems had an effect on Cronbach's alpha. (SLD)