Thirty-one clinical psychologists scored Comprehension, Similarities, and Vocabulary subtest items common to the Wechsler Intelligence Scale for Children (WISC) and the Wechsler Intelligence Scale for Children, Revised (WISC-R). The results on interrater scoring agreement suggest that the scoring of these subtests may be less subjective than…

The extent to which one can reduce the rank of a symmetric matrix by only changing its diagonal entries is discussed. Extension of this work to minimum trace factor analysis is presented. (Author/JKS)

The proportion of agreement, G, and kappa indexes are shown to differ in how they correct for chance agreements between two observers. On the basis of the findings, it is suggested that no single agreement index is appropriate for all sets of data. (Author/BW)

The sole objective of the employment interview should be to obtain and evaluate factual and verifiable information. The greater the discrepancy between the tasks of the job and the experience of the interviewee, the more critical will be the influence of the intuitive judgment of the interviewer. (Author/MLF)

Since fixed and random facets may exist in objects of study as well as in conditions of observation, various modifications of the generalizability theory estimation formulas are required for different types of measurement designs. Various design modifications are proposed to improve reliability by reducing error variance. (Author/BW)

The use of a quasi-equiprobability model in the measurement of observer agreement involving dichotomous coding categories is described. A measure of agreement is presented which gives the probability of agreement under the assumption that observation pairs reflecting disagreement will be equally probable. (Author/JKS)

Kaiser and Michael reported a formula for factor scores giving an internal consistency reliability and its square root, the domain validity. Using this formula is inappropriate if variables are included which have trival weights rather than salient weights for the factor for which the score is being computed. (Author/RL)

The study reported differences in agreement among four experienced listeners who analyzed the articulation skills of 97 four- and five-year-old children. Place and manner of articulation revealed differences of agreement, whereas voicing and syllabic function contributed little to agreement or disagreement. (Author)

Research indicates that three samples may not give a good indication of a workbook's narrative readability level. (MKM)

Investigating use of maximum v averaged scores in physical and motor multiple-trial tests as indicators of performance, this article concludes use of mean scores is still most appropriate in terms of scientific estimations of true performance given multiple fallible empirical measures. (JC)

The present study was designed to determine if maze tests constructed over the same passages by different teachers were comparable. In addition, maze test parallel form reliability was investigated. (HOD)

The one-year stabilities of several well-standardized intellectual, educational, and personality tests were evaluated for 15 children of Mexican American migrant workers. Most of the stability coefficients observed for these tests were statistically significant and similar to those reported for their normative samples. However, the stability…

Use of the same term "split-half" for division of an n-item test into two subtests containing equal (Cronbach), and possibly unequal (Guttman), numbers of items sometimes leads to a misunderstanding about the relation between Guttman's maximum split-half bound and Cronbach's coefficient alpha. This distinction is clarified. (Author/JKS)

Two doctoral level school psychologists independently scored 50 McCarthy drawing booklets. Children producing the drawings ranged from 5-11. Interscorer reliability for Draw-A-Design was .93 and for Draw-A-Child was .96. No significant differences occurred in the mean score for either test across scores. (Author)

An introduction is provided to the use of confirmatory factor analysis to test measurement invariance and stability in longitudinal research. The approach is illustrated through examples representing one or two constructs in one to three measurement waves. Basic issues in establishing measurement invariance are discussed. (SLD)