The agreement of diagnostic classifications from two parallel subtests assessing a mathematics skill with three levels of scoring was studied with 431 Arab Israeli 10th graders. Results indicate that, even when parallel form reliability is high, less agreement is apparent when performance is evaluated at the micro level. (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)

Investigated whether dimensions of transformational and transactional leadership can be inferred from subordinate reports of leadership behaviors collected through the Leadership Practices Inventory (LPI) (B. Posner and J. Kouzes, 1988) completed by 1,892 subordinates about 344 managers. Results support use of the LPI to measure transformation and…

Ability estimates obtained from applying finite state score theory, item response models, and classical test theory to score multiple-choice items were compared using responses of 1,230 examinees. Scoring models provided essentially the same ranking of examinees, but ease of use and interpretation support the use of the classical test model. (SLD)

A test-retest study of the Myers-Briggs Type Indicator with 99 graduate students over 20 months yields findings consistent with previous studies, but an examination of type dynamics using log-linear analyses indicates that dominant thinking and dominant sensing do not retest as well as dominant intuition and feeling. (SLD)

Methods are offered for conducting hypothesis testing associated with disattenuated validity coefficients to overcome limitations of some other suggested approaches. Through using classical test theory's notion of reliability in the form of structured path models, such hypothesis testing may be done with hierarchically related structural equation…

The feasibility and efficacy of using self-report response methods with an In-Basket exercise were evaluated in two studies involving 258 managers and 55 college students, respectively. Results suggest that high face validity of the In-Basket exercise can be combined with the scoring ease and objectivity of self-reports. (SLD)

Although Camp's tetrachoric correlation approximation (B. Camp, 1934) has been shown to yield excellent results over a fairly wide range, its derivation remains something of a mystery. This article shows how Camp might have arrived at his formula using a theoretical, rather than an empirical, approach. (Author/SLD)

Several methods of constructing confidence intervals for Spearman's rho (rank correlation coefficient) (C. Spearman, 1904) were tested in a Monte Carlo study using 2,000 samples of 3 different sizes. Results support the continued use of Spearman's rho in behavioral research. (SLD)

Some results on how the Alexander-Govern heteroscedastic analysis of variance (ANOVA) procedure (R. Alexander and D. Govern, 1994) performs under nonnormality are presented. This method can provide poor control of Type I errors in some cases, and in some situations power decreases as differences among the means get large. (SLD)

The convergent validity of peer, self, and teacher methods of assessing youths' risk propensity and the relation of these measures to health risk behavior were studied with 436 elementary and junior high school students. Findings demonstrate low congruence between rater sources. Prediction depended on behavior assessed and grade level. (SLD)

A study involving 209 Spanish high school students compared computer-based English vocabulary tests: (1) a self-adapted test (SAT); (2) a computerized adaptive test (CAT); (3) a conventional test; and (4) a test combining SAT and CAT. No statistically significant differences were found among test types for estimated ability or posttest anxiety.…

The Time Structure Questionnaire (M. J. Bond and N. T. Feather, 1988) and the Time Management Behavior Scale (T. H. Macan and colleagues, 1990) were evaluated through results from 701 and 453 adults respectively. Results confirm the importance of examining subscales of these measures rather than simply aggregate scores. (SLD)

Ethnic and gender differences in motivation to manage were studied through sentence completion tests and in-basket exercises completed by 138 White, 9 American Indian, 28 Black, 64 Hispanic, 44 Asian, and 5 "other" college students. Both types of differences were found. Implications for identification of management talent are discussed. (SLD)

A Monte Carlo study compared the accuracy of different estimates of the standard error of correlations corrected for restriction in range. The procedure suggested by P. Bobko and A. Rieck (1980) generated the most accurate estimates of the standard error. Aspects of accuracy are discussed. (SLD)