Studied four different approaches for handling missing data for their capacity to mitigate against the effect of omitted responses on person location estimation. Results from a Monte Carlo study show that the hot-decking procedure performed best of the methods examined. (SLD)

Developed a hybrid procedure for number correct scoring that uses test item weights based on multidimensional item response theory and total test scores based on classical true score theory. Simulation results show that all scoring methods in the study generated estimated and true scores that were highly correlated, but the hybrid method resulted…

Discusses the new venture decision process and reports on the development and results of this innovative decision exercise designed to help entrepreneurship students experience the process firsthand. (Author)

An alternate type of simulation was developed that might make the study of accounting more relevant and the retention of the material greater. Half of the students completed a conventional business practice set; half created a simulated business, designed an accounting system, and constructed transactions. (JOW)

A split-sample replication stopping rule for hierarchical cluster analysis is compared with the internal criterion previously found superior by Milligan and Cooper (1985) in their comparison of 30 different procedures. Situations under which the methods are equivalent or not equally useful are discussed. (SLD)

Type I error rates for the Mantel-Haenszel (MH) statistic were within nominal limits when the MH procedure was compared with the simultaneous item bias (SIB) method for detecting differential item functioning. Results with data simulated for 1,296 conditions found Type I error rates slightly higher than expected for SIB. (SLD)

Discussion of the use of consensus-building techniques to resolve public policy disputes focuses on the use of a simulation of the conflict that needs to be resolved. An example is given of the National Energy Policy Simulation that was designed by the Massachusetts Institute of Technology (MIT)-Harvard Public Disputes Program. (38 references)…

A recursive equation is proposed for computing higher order derivatives of elementary symmetric functions in the Rasch model. A simulation study indicates a small loss in accuracy for the proposed formula compared to Gustafsson's sum algorithm (1980) for computing higher order derivatives when tests contain 60 items or less. (SLD)

A simple procedure for measuring changes in the acoustic impedance of the ear is described. The technique has several applications, including simulation using a standard coupler of changes in real ear impedance produced by the acoustic reflex, and calibration of response time of an otoadmittance meter. (Author/DB)

Discussion of the interpolation methodology expounded by Goosen and Kusel to model business functions for simulation design criticizes the approach's simplicity because interactive effects between variables in the functional relationships are not considered. (six references) (EA)

Advantages of simulation are link between classroom and real experience, experiment with risk, intensive focus, and reflection on experience. It can involve rigorous and time-consuming preparation, unpredictable outcomes, and trainee resistance. Facilitators need good coaching skills and personal sensitivity. (SK)

Meaningful role plays have three phases: warm-up, which creates an environment that fosters interaction and overcomes resistance; action, during which protagonists and auxiliaries are chosen and the action is periodically frozen for reflection and feedback; and closure, to reinforce learning and plan its integration into job performance. (SK)

Investigated the effects of types and prevalence of response patterns that might be provided by nonattending respondents on Cronbach's alpha (L. Cronbach, 1970) using three simulated data sets. Effects were greater as a function of increased prevalence in the respondent group, but as few as 5% of some types of nonattending patterns had inflating…

Examined the effects of model misspecification on the precision of decisions made using the sequential probability ratio test (SPRT) in computer testing. Simulation results show that the one-parameter logistic model produced more errors than the true model. (SLD)

Examined the optimal value of "k" for promax factor rotations through a Monte Carlo study involving 10,080 factor analyses. Results show that in factor-analytic studies using promax, the value of "k" may be set appropriately at 2, 3, or 4. (Author/SLD)