Skew and internal consistency.

The effects of skew on the standardized item alpha were examined with Monte Carlo techniques. Alphas computed from normal variables were compared with alphas from lognormal variables, ranks, and skewed versus normal Likert-type variables. The extent and direction of skew were varied, as was the size of the population interitem correlation (rho), the number of items, and the number of categories for Likert-type variables. Because the average interitem correlation affects alpha and skew affects the average interitem correlation, the effect of skew on the average interitem correlation also was examined. Results indicated that skew decreased the average interitem correlation and produced small decreases in alpha that were largest when skew was large, rho was small, items were skewed in opposite directions, and there were fewer items. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The internal consistency of the Humm-Wadsworth Temperament Scale.

For 508 male industrial applicants, a revised Likert analysis failed to substantiate unidimensionality. Reasons ascribed these results are ambiguous definitions and item formulation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the readability on the Position Analysis Questionnaire (PAQ).

The Position Analysis Questionnaire (PAQ) is a structured job analysis questionnaire composed of worker-oriented job elements. 4 readability indexes--the Date-Chall, the Flesch, the FOG (R. Gunning), and the SMOG (H. McLaughlin)--were applied to both the directions and questions of the PAQ. The PAQ directions reach a college readability level using the Flesch and SMOG indexes and reach the college graduate level using the Dale-Chall and FOG indexes. The PAQ questions reach the college graduate readability level on all 4 indexes. Implications regarding the use of the PAQ in light of its difficult level of readability are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A meta-analysis of interrater and internal consistency reliability of selection interviews.

A meta-analysis of 111 interrater reliability coefficients and 49 coefficient alphas from selection interviews was conducted. Moderators of interrater reliability included study design, interviewer training, and 3 dimensions of interview structure (standardization of questions, of response evaluation, and of combining multiple ratings). Interactions showed that standardizing questions had a stronger moderating effect on reliability when coefficients were from separate (rather than panel) interviews, and multiple ratings were useful when combined mechanically (there was no evidence of usefulness when combined subjectively). Average correlations (derived from alphas) between ratings were moderated by standardization of questions and number of ratings made. Upper limits of validity were estimated to be .67 for highly structured interviews and .34 for unstructured interviews. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The internal consistency of measures of cognitive structure.

The distribution of judgments between alternative poles of a construct, derived from the grid form of the Role Construct Repertory Test, influences the interpretation of measures of cognitive structure. Investigations of the reliability of these measures have excluded the possibility that differentiation on the basis of similarity is distinct from differentiation on the basis of contrast. In the present study with 107 business school students, judgments of similarity were assumed to be different from those of contrast. The present evaluation of internal consistency, temporal stability, and construct validity for 10 measures of cognitive structure indicates that only 1 measure satisfies criteria on these 3 attributes. (French abstract) (35 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Coefficient alpha and related internal consistency reliability coefficients.

The author studied the conditions under which coefficient alpha and 10 related internal consistency reliability coefficients underestimate the reliability of a measure. Simulated data showed that alpha, though reasonably robust when computed on n components in moderately heterogeneous data, can under certain conditions seriously underestimate the reliability of a measure. Consequently, alpha, when used in corrections for attenuation, can result in nontrivial overestimation of the corrected correlation. Most of the coefficients studied, including lambda2, did not improve the estimate to any great extent when the data were heterogeneous. The exceptions were stratified alpha and maximal reliability, which performed well when the components were grouped into two subsets, each measuring a different factor, and maximized lambda4, which provided the most consistently accurate estimate of the reliability in all simulations studied. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Age, education, and the internal consistency of personality scales.

Investigated whether the internal consistencies of personality scales increase with age and education and, if so, what causes these increases. Between 96 and 106 respondents in each of the age groups 13–24 yrs, 15–26 yrs, 17–28 yrs, and 19–20 yrs and 198 adults (aged 21–25 yrs) with varying amounts of formal education completed the Taylor Manifest Anxiety Scale, the California F-Scale, the Marlowe-Crowne Social Desirability Scale, a dogmatism scale, the Extraversion subscale of the Eysenck Personality Inventory, a self-monitoring scale, and a private self-conscious scale. Results show that age and education were both linearly related to the internal consistency with which Ss responded to all 8 personality scales. The relations were stronger for education than for age, the correlations between individuals' consistency scores across scales revealed a strong consistency response set. Stepwise regression showed that this internal consistency was related to age, education, the failure to understand items, and private self-consciousness. These last 2 contributions suggest that lower consistencies are partly a measurement problem and partly due to real lower personality consistencies on trait constructs. It is suggested that, because most personality research has used nonadults, the lower internal consistency of the younger Ss has contributed to the limited predictive power of personality scales. (35 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the criterion.

The concept of the criterion in much applied research has implied the possibility of identifying a single, ultimate measure against which predictors should be correlated. It is argued that the criterion has been overemphasized with the result that complexities of predicting the many facets of job success have been ignored in favor of overly simplified studies designed to relate predictors to single measures of job success. Applied psychologists should give more emphasis to construct validation and make an effort to learn more about the meaning of test scores and other predictors in terms of multiple dimensions of behavior. Information available on the Engineering Research Key of the Strong Vocational Interest Blank is presented in order to illustrate the pattern of validation research recommended. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The relationship between social desirability and internal consistency of personality scales.

3 hypotheses concerning the relationships between psychometric characteristics of 61 personality scales were tested. A measure of internal consistency (Kuder-Richardson Formula 21) was found to be positively correlated (.62) with the degree of imbalance in the social desirability keying of the scales. Internal consistency was also negatively correlated (-.46) with the proportion of neutral items in the scales. The mean probability of a keyed response to the items in a scale was positively correlated (.83) with the proportion of items keyed for socially desirable responses. These results are consistent with predictions based upon social desirability considerations. (19 ref.) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Psychometric inferences from a meta-analysis of reliability and internal consistency coefficients.

A meta-analysis of the reliability of the scores from a specific test, also called reliability generalization, allows the quantitative synthesis of its properties from a set of studies. It is usually assumed that part of the variation in the reliability coefficients is due to some unknown and implicit mechanism that restricts and biases the selection of participants in the studies' samples. Sometimes this variation has been reduced by adjusting the coefficients by a formula associated with range restrictions. We propose a framework in which that variation is included (instead of adjusted) in the models intended to explain the variability and in which parallel analyses of the studies' means and variances are performed. Furthermore, the analysis of the residuals enables inferences to be made about the nature of the variability accounted for by moderator variables. The meta-analysis of the 3 studies' statistics—reliability coefficient, mean, and variance—allows psychometric inferences about the test scores. A numerical example illustrates the proposed framework. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on projection.

Projection if defined as "unwittingly attributing one's own traits to others" may be either defensive or predictive. It still needs much research effort. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the dynamic correlation coefficient.

Examined the use of the dynamic correlation coefficient as a test of spuriousness in longitudinal designs. It is shown that given conditions of spuriousness and perfect stationarity, the dynamic correlation coefficient was positively, rather then inversely, related to spuriousness. It is also shown that very high dynamic correlations were indicative of spuriousness and that low to moderate dynamic correlations may reflect a number of conditions. It is concluded that the dynamic correlation is, in many instances, a highly fallible indicator of spuriousness. (19 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the Nagle attitude scale.

Nagle's scale to measure attitude toward supervisor assumed a relationship between an attitude toward the supervisor and a perception of how he behaves. This assumption was rejected by Brayfield and Crockett (1955). Evidence is now presented in support of the assumption and in rebuttal to Brayfield and Crockett. A special scale to measure attitudes toward supervisors was constructed specifically to avoid items referring to overt behavior. The correlation between the 2 scales for 74 research engineering employees was .786, or .835 when corrected for attenuation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the scoring of ego disjunction.

A statistical reanalysis of the findings presented previously (see 34: 1064) demonstrated that the method of measuring ego disjunction was not as effective in distinguishing schizophrenics, character disorders, and college students as has been reported. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the stability of team performance.

Yearly winning percentages of 23 professional basketball teams over a 10-year period were used to evaluate the stability of team performance. The intercorrelation matrix produced by these data is characterized by strong, positive correlations in adjacent time periods. As the number of intervening time periods increased, however, the observed correlations systematically decreased and ultimately became negative. Significant negative correlations of earlier performance with later performance are almost never observed with typical time-related performance data. Possible explanations and boundary conditions for these atypical results are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on the judgment of speaker effectiveness.

Ratings of the effectiveness of the speaker at each of 14 meetings (445 participants, some attending more than 1 meeting) on an 8-item rating scale showed that a simple rating procedure can yield useful discrimination as to the excellence of public-speaker addressed meetings. However, this discrimination is primarily on a general or overall factor, with little evidence of differentiation among such elements as the speaker's qualifications or ability, topic coverage, personal gain from meeting, or satisfaction of expectations. Ratings of "timeliness of topic" alone tended to be somewhat independent of the evaluation of the meeting itself. Ratings of the effectiveness of the speaker were not significantly correlated with attendance at the meetings. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A note on analysis of covariance.

S. H. Evans and E. J. Anastasio (see record 1968-09688-001) constructed 2 sets of hypothetical data to show ways in which the analysis of covariance can yield erroneous results. It is argued that analysis of covariance does not give incorrect results for either set of their data. Analysis of covariance correctly (within rounding error) recovered the form of the models used to construct their data and also provided accurate estimates of parameters for both sets of data. Although analysis of covariance produces accurate results, it must be used cautiously because it may or may not answer the substantive question a researcher asks. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A further note on the fakability of the MTAI.

"This study employed a factorial design to investigate the effects of several conditions of administration on the fakability of the MTAI… the findings support the conclusion that groups of students are not likely to be able to fake the MTAI unless they receive a cue from the faking instructions, or elsewhere, as to what the inventory is about." (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A further note on ranking the important psychologists.

Responses of 246 American Psychological Association members (of 1,000 surveyed) ranked Freud, Skinner, Watson, Pavlov, and Hull, respectively, as having the greatest influence on 20th century psychology. Skinner, Rogers, Hebb, Piaget, and Harlow, respectively, were ranked as the 5 most influential contemporary contributors. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A cautionary note.

Cautions psychologists to reexamine the desirability of exporting to other cultures the motivational traits that may be responsible for the environmental threats facing technologically advanced nations. Socially concerned scientists have an ethical responsibility to examine the consequences of applying their knowledge before pursuing the means of implementation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)