Computer simulations were employed to investigate sample sizes needed for item analysis when one's primary purpose is to rank order items in terms of indices of quality or to compare indices of quality against a fixed criterion. Necessary sample sizes were much smaller than those indicated by the literature. (Author/JKS)

A computer program to generate individualized objective test forms for use in a Student Faced Statistics (SPS) course is described. The program features disproportionate sampling from different item domains and enhanced character generation facility for test printing purposes. (Author)

An examination question is presented which involves a scheme to salvage the sunken ship Edmond Fitzgerald by generating hydrogen gas inside it using electrolysis. (BB)

A total of 102 undergraduates rated overt test integrity items on the dimensions of invasion of privacy, ease of faking, and job relatedness. Items that required direct admission of counterproductive behaviors were identified as the most invasive but also the easiest to fake. Implications for test construction and future research are discussed.…

Two possible standard error formulas for the polytomous differential item functioning index proposed by N. J. Dorans and A. P. Schmitt (1991) were derived. These standard errors, and associated hypothesis-testing procedures, were evaluated through simulated data. The standard error that performed better is based on N. Mantel's (1963)…

Using a multidimensional measure of pay satisfaction, the Pay Satisfaction Questionnaire (PSQ), this study assessed the discriminant validity between scores on a measure of distributive justice and the PSQ with 474 employees. Confirmatory factor analysis results indicate that items from both scales loaded on the hypothesized dimensions. (SLD)

Using the characteristic curve method for dichotomously scored test items, the sampling distributions of equating coefficients were examined. Simulations indicate that for the equating conditions studied, the sampling distributions of the equating coefficients appear to have acceptable characteristics, suggesting confidence in the values obtained…

Presents a validation procedure for cognitive structures that is based on structural equation modeling of cognitive subordination relationships among test items. Illustrates the method using scores of 278 ninth graders on an algebra test and shows results for the same test when the linear logistic test model is used. (SLD)

Five analyses using Korean college students (n=283, 700, 844, 306, 315) were conducted to develop the Korean Career Indecision Inventory. Five factors emerged consistently and were confirmed by factor analysis: lack of career information, lack of necessity recognition, lack of self-identity, indecisiveness, and external barriers. Reliability and…

Explored procedures to detect test takers using item preknowledge in computerized adaptive testing and suggested a Bayesian posterior log odds ratio index for this purpose. Simulation results support the use of the odds ratio index. (SLD)

A simple approximation to the conditional distribution of goodness-of-fit statistics for the Rasch model is presented that is used when item difficulties are known. The approximation, which is easily programmed, gives relatively accurate assessments of conditional p-values for tests of 10 or more items. (Author/SLD)

A modification of the Mantel Haenszel (MH) procedure in which the sample is broken in half and subsamples are studied separately was compared with a residual procedure based on item response theory as a way to detect differential item functioning (DIF). Results suggest that the residual analysis achieves higher DIF detection. (SLD)

The importance of item feedback in self-adapted testing was studied by comparing feedback and no feedback conditions for computerized adaptive tests and self-adapted tests taken by 363 college students. Results indicate that item feedback is not necessary to realize score differences between self-adapted and computerized adaptive testing. (SLD)

Four studies of the factorial validity of the Spatial Learning Ability Test (SLAT), involving 431 undergraduates, were summarized to elaborate nomothetic span. These studies support the SLAT as a spatial processing measure. The SLAT, compared to a test with the same item type, was a more pure measure of spatial ability. (SLD)

For measurement of multiple traits, this paper proposes assembling tests based on the targets for the variance functions of the estimators of each of the traits. A linear programming model is presented to computerize the assembly process. An example of test assembly from a two-dimensional item pool is provided. (SLD)