Showing papers in "Educational and Psychological Measurement in 1974"
TL;DR: In this article, a step-by-step computer algorithm of the revised version of the original Little Jiffy, Mark IV, is presented, with the index of the covariance matrix (with zero in the diagonal) under consideration.
Abstract: IN this paper three changes and one new development for the method of exploratory factor analysis (a second generation Little Jiffy) developed by Kaiser (1970) are described. Following this short description a step-by-step computer algorithm of the revised method-dubbed Little Jiffy, Mark IV-is presented. Extensive empirical experience with &dquo;a second generation Little Jiffy&dquo; (Kaiser, 1970) indicates that the method, for large matrices, consistently mildly underfactors. A revision is called for. Thus, the writers adopt as the answer for the crucially important question of the &dquo;number of factors&dquo; Guttman’s (1954) classic weaker lower bound, the index of the covariance matrix (with zeros in the diagonal) under consideration. This answer is the same as that given by Kaiser’s (1956, 1960, 1970) extensively used &dquo;eigenvalues greater than one of R.&dquo;
2,161 citations
TL;DR: In this paper, Joreskog's general model for the analysis of covariance structures is used to test the validity of the assumption that correlation reliablity estimates are equivalent.
Abstract: Intraclass correlation reliablity estimates are based on the assumption that the various measures are equivalent. Joreskog's (1970) general model for the analysis of covariance structures can be used to test the validity of this assumption.
1,542 citations
TL;DR: In this article, it was shown that traditional and negative suppressors increase the predictive value of a standard predictor beyond that suggested by the predictor's zero order validi cation in the two-predictor situation.
Abstract: In the two-predictor situation it is shown that traditional and negative suppressors increase the predictive value of a standard predictor beyond that suggested by the predictor's zero order validi...
595 citations
TL;DR: In this paper, a short-form administration of the MMPI is described, which consists of the first 168 items of the standard MMPIs and can be used to estimate k-corrected clinical scale scores by application of regression weights.
Abstract: A convenient short-form administration of the MMPI is described. Rather than selecting items out of context, it is recommended that the abbreviated administration consist of the first 168 items of the standard MMPI. The usual scoring stencils can be applied to obtain scores which can be used to estimate k-corrected clinical scale scores by application of regression weights.
121 citations
TL;DR: In this paper, the authors compared the ANOVA F-test, the Kruskal-Wallis test, and the normal scores test in terms of empirical alpha and empirical power with samples from the normal distribution and two exponential distributions.
Abstract: The present research compares the ANOVA F-test, the Kruskal-Wallis test, and the normal scores test in terms of empirical alpha and empirical power with samples from the normal distribution and two exponential distributions. Empirical evidence supports the use of the ANOVA F-test even under violation of assumptions when testing hypotheses about means. If the researcher is willing to test hypotheses about medians, the Kruskal-Wallis test was found to be competitive to the F-test. However, in the cases investigated, the normal scores test was not consistently better than the F-test or the Kruskal-Wallis test and could not be recommended on the basis of this research.
118 citations
TL;DR: A two-factor analysis of variance with multiple measurements on one factor was conducted among the 40 items of the Vocabulary test of TOEFL for six language groups as discussed by the authors, and all sources of variance were found to be significant beyond the one per cent level.
Abstract: A two-factor analysis of variance with multiple measurements on one factor was conducted among the 40 items of the Vocabulary test of TOEFL for six language groups. All sources of variance were found to be significant beyond the one per cent level. Of particular interest was the item x group interaction which was examined by analyzing the item difficulty plots for each language group against a spaced sample of all candidates taking this form of the test at its first formal administration. A measure of the deviation of each item from the central tendency of the plot was developed, expressing the degree to which the item was especially difficult or especially easy for a particular language group relative to the other items. A distribution of these measures is given for each of the six language groups.
46 citations
TL;DR: In this paper, student and alumni ratings for 23 teachers were found to correlate.75 (somewhat less for teachers rated only by graduates of their department) with student and alumnus ratings.
Abstract: Student and alumni ratings for 23 teachers were found to correlate .75 (somewhat less for teachers rated only by graduates of their department). This substantial agreement between current students and alumni (of five years) regarding who have been effective or ineffective teachers suggests a good deal of persistence in judgments of teachers by students.
46 citations
TL;DR: In this paper, the authors derived a graphical approximation of the item parameters of the stochastic mental test models, i.e., the generalized normal ogive and logistic models.
Abstract: Equations were derived to enable the graphic approximation of the item parameters of the stochastic mental test models, i.e., the generalized normal ogive and logistic models. The item parameters for the models are discriminatory power (ai), difficulty (bi), and lower asymptote of the item characteristic curve (ci) where the item characteristic curve (ICC) is the regression of the binary item on latent ability. In brief, c i can be approximated through visual inspection of the left-hand (lower) asymptote of the proportion passing the item plotted against the total test score minus the particular item. Thereafter, a graph appropriate to the approximate ci can be consulted to convert an ordinary item-total test point-biserial correlation and proportion passing the item into approximations of item discriminatory power (ai) and item difficulty (bi). Suggested uses for the approximations were to provide a basis for screening items for tailored testing, to enable a determination as to the appropriateness of a s...
46 citations
TL;DR: Theoretical problems with the factor analysis model have resulted in increased interest in component analysis as an alternative as mentioned in this paper, and it is therefore of interest to assess empirically some of the assert...
Abstract: Theoretical problems with the factor analysis model have resulted in increased interest in component analysis as an alternative. It is therefore of interest to assess empirically some of the assert...
35 citations
TL;DR: A number of scales, including the Ohio State leadership scales, use the response categories Always, Often, Occasionally, Seldom, and Never as mentioned in this paper, and researchers administering these scales usually assume...
Abstract: A number of scales, including the Ohio State leadership scales, use the response categories Always, Often, Occasionally, Seldom, and Never, and researchers administering these scales usually assume...
33 citations
TL;DR: A factor analysis of 30 measures of the Torrance Tests of Creative Thinking administered to a sample of 111 sixth-grade pupils revealed that each of the seven rotated factors described a task (content) rather than an hypothesized psychological process for which a task was scored.
Abstract: A factor analysis of 30 measures of the Torrance Tests of Creative Thinking administered to a sample of 111 sixth-grade pupils revealed that each of the seven rotated factors described a task (content) rather than an hypothesized psychological process for which a task was scored.
TL;DR: In this paper, a review was made of recently published research articles concerning the predictive validity of the scores on the GRE relative to the criteria of grade point average and general success in graduate school.
Abstract: Because of the wide usage of the Graduate Record Examination (GRE) as a selection instrument and the general acceptance of its predictive ability, a review was made of recently published research articles concerning the predictive validity of the scores on the GRE relative to the criteria of grade point average and general success in graduate school. The data from the articles reviewed were reported, and the weight of the evidence suggests that this wide usage of the GRE as a selection instrument must be questioned. These data also illustrate the need for additional predictive studies in this area as none of the results were found to be conclusive.
TL;DR: In this paper, a method for multidimensional scaling of dichotomous item data is presented which is derived from ordering theory, which is related to the methodological multivariate extension of Guttman...
Abstract: A method for the multidimensional scaling of dichotomous item data is presented which is derived from ordering theory. This method is related to the methodological multivariate extension of Guttman...
TL;DR: In this article, a measure of the magnitude of the effect in a one-factor multivariate analysis of variance design is considered, which is based on the use of |W| as the estimate of a generalized measure of within-groups variation and |T| as an estimate of the total variation, and it is argued that crM = 1 - Tr(WW-1)/ Tr(TW -1) is a more suitable multivariate generalization of the univariate correlation ratio.
Abstract: A measure of the magnitude of the effect in a one-factor multivariate analysis of variance design is considered. Cooley and Lohnes have proposed the use of the quantity (1 — |W|/|T|) as a multivariate extension of the correlation ratio, where |W| is the determinant of the within-groups cross-products matrix and | T| is the determinant of the total cross-products matrix. The measure is based on the use of |W| as the estimate of a generalized measure of within-groups variation and |T| as the estimate of a generalized measure of total variation. If a multivariate correlation ratio is defined as the proportion of variance in the multivariate domain predictable from the factor, it is argued that crM = 1 - Tr(WW-1)/ Tr(TW -1) is a more suitable multivariate generalization of the univariate correlation ratio.
TL;DR: Men did perform at a significantly higher level than women did on the Watson-Glaser instrument, and this performance was associated with their significantly higher performance in the subtests of Inference and Evaluation of Arguments as mentioned in this paper.
Abstract: Seventy-nine third year British university students were randomly selected and tested on the Watson-Glaser Critical Thinking Appraisal and the Eysenck Personality Inventory.Men did perform at a significantly higher level than women did on the Watson-Glaser instrument, and this performance was associated with their significantly higher level of performance in the subtests of Inference and Evaluation of Arguments. There was no difference in performance which could be related to enrollment in an Arts or Science course, except for the test of Inference in which Science students did have a very significantly higher score than Arts students did. Performance on the Watson-Glaser instrument was not significantly associated with scores of extroversion-introversion on the Eysenck Personality Inventory.
TL;DR: In this article, item responses of two samples of normal and educable mentally retarded (EMR) children on Raven's Coloured Progressive Matrices were submitted to a principal components analysis and varimax rotation.
Abstract: Item responses of two samples of normal and educable mentally retarded (EMR) children on Raven's Coloured Progressive Matrices were submitted to a principal components analysis and varimax rotation...
TL;DR: The process culminating in the response to an item in a personality inventory affects the value of that response's contribution to test score as discussed by the authors, and some response components are inappropriate from the ex...
Abstract: The process culminating in the response to an item in a personality inventory affects the value of that response's contribution to test score. Some response components are inappropriate from the ex...
TL;DR: In this paper, the effect of the number of scale intervals of a continuous variable on the results of principal components factor analysis was investigated, and the general effect was a decrease in the size of the eigenvalues, communalities, and factor loadings as the numbers of scale divisions was reduced.
Abstract: The effect of the number of scale intervals of a continuous variable on the results of principal components factor analysis was investigated. Analyses were performed for seven different numbers of scale intervals. The general effect was a decrease in the size of the eigenvalues, communalities, and factor loadings as the number of scale divisions was reduced. The magnitude of the effect was, however, not large and the pattern of the rotated factor loadings was not appreciably affected.
TL;DR: In this article, the Torrance Tests of Creative Thinking were used to ascertain the relationships between a creative personality measure, What Kind of Person Are You? Test, and three verbal and four figural creative ability measures derived from the Torrence Tests of creative thinking.
Abstract: Persons with creative abilities might be expected to have creative personality characteristics. The purpose of this study was to ascertain the relationships between a creative personality measure, What Kind of Person Are You? Test, and three verbal and four figural creative ability measures derived from the Torrance Tests of Creative Thinking. The subjects were 65 males and 164 female undergraduates enrolled in the introductory course in educational psychology at the University of Georgia. For the males, multiple coefficients of correlation were .57 for all seven creative ability measures, .42 for the three verbal measures, and .51 for the four figural measures (all significant at the .01 level). For the females, multiple coefficients of correlation were .33 for all seven measures, .22 for the three verbal measures, and .30 for the four figural measures (all significant at or beyond the .05 level).
TL;DR: A sample of 529 nonurban high school students each responded to one of four test forms which differed in subject matter (natural science or social studies) and item form order (true-false items bef...
Abstract: A sample of 529 nonurban high school students each responded to one of four test forms which differed in subject matter (natural science or social studies) and item form order (true-false items bef...
TL;DR: In this study tailoring was simulated with 100 Monte Carlo "examinees" for four different item banks and the estimate of ability obtained was compared with the known true ability of each "examine" as each S.E.E level was reached.
Abstract: There are two general ways to terminate the Bayesian tailored testing process:, according to the standard error of the estimate (S.E.E.) or according to the number of items administered. In this st...
TL;DR: This paper investigated the extent to which various traditional measures (test scores, undergraduate GPA, and letters of recommendation) and less traditional measures(interview ratings and biographical information) would predict each of two criteria of success in a subdoctoral program in applied psychology: (a) academic competency defined as grade point average (GPA) in graduate school, and (b) faculty ratings of selected interpersonal skills.
Abstract: This study investigated the extent to which various traditional measures (test scores, undergraduate GPA, and letters of recommendation) and less traditional measures (interview ratings and biographical information) would predict each of two criteria of success in a subdoctoral program in applied psychology: (a) academic competency defined as grade point average (GPA) in graduate school, and (b) faculty ratings of selected interpersonal skills.The traditional measures were significantly but modestly related to academic competency. The use of biographical information and interview ratings was supported in selecting for interpersonal skills. Ratings of letters of recommendation failed to show a relationship to either GPA or ratings of interpersonal skills.
TL;DR: This paper presents a method for identifying and analyzing the nature of test bias, intended as only a preliminary analysis prior to, or concurrently to, a criterion data collection process.
Abstract: The problem of test bias has been a growing concern in recent years. Of the several available methods for determining test bias, probably the most effective means involves collecting criterion information. This data collection process often provides a considable barrier to the researcher, especially for the small test user and for someone who needs an immediate solution to a test bias question. This paper presents a method for identifying and analyzing the nature of test bias. This method is intended as only a preliminary analysis prior to, or concurrently to, a criterion data collection process.
TL;DR: In this paper, the predictive validity of the CEEB SAT scores in the prediction of grades earned by a randomly chosen sample of 142 women in freshman mathematics at Longwood College was determined.
Abstract: The purpose of this study was to determine the predictive validity of the CEEB SAT scores in the prediction of grades earned by a randomly chosen sample of 142 women in freshman mathematics at Longwood College. Data consisted of SAT-V, SAT-M, and SAT-T scores and the grade earned in freshman mathematics for 706 female students who entered Longwood College in August, 1973. The SAT-T and the SAT-M scores yielded substantial correlations of .63 and .62 with earned grades in freshman mathematics. There was a .48 correlation between SAT-V scores and earned grades in freshman mathematics. All correlations were statistically significant beyond the .01 level.
TL;DR: In this paper, items from a standardized reading test designed to measure the ability to identify the main ideas of paragraphs were administered without the associated paragraphs, and two samples consisted of graduate students and inner-city high-school students.
Abstract: Items from a standardized reading test designed to measure the ability to identify the main ideas of paragraphs were administered without the associated paragraphs. The two samples consisted of graduate students and inner-city high-school students. A random half of each sample was given brief, general directions for answering the items in the absence of the passages, and the other half was given more extensive directions for answering the items in the absence of the passages. The different directions did not have a significant effect on performance, but both halves of the two samples answered a substantial number of items correctly. An index of passage-dependence was computed for each item, and the index values obtained from the responses of the graduate students and high-school students were substantially correlated.
TL;DR: The study showed that boys did score slightly higher on the PM than did the girls, the differences being significant up to age 13, but the differences were not significant beyond age 15.
Abstract: This study reports the results of the application of Raven's Progressive Matrices (PM) to a representative sample of Iranian children attending schools in Teheran, the capital city of Iran. The study showed that boys did score slightly higher on the PM than did the girls, the differences being significant up to age 13. There was a consistent increase in PM scores at successive age levels, but the increments were not significant beyond age 15. Iranian children scored considerably below the British norms, although this decrement might have been due to the timed administration of PM in Iranian samples and to a variety of cultural factors. The reliability and validity of the PM were found to be satisfactory. Although the findings indicated the general suitability of the PM for use with Iranian children, there is a need for further normative and validity studies.
TL;DR: This paper tested the validity of the College-Level Examination Program's General Examination in English Composition (CLEP) and found that the CLEP can validly be used to excuse Utah State University students from FE.
Abstract: The present study tested the validity of the College-Level Examination Program's General Examination in English Composition (CLEP). With essay and objective tests as the criteria of writing performance, groups of Utah State University students that had completed Freshman English (FE Group) were compared with groups of Utah State University students who had been excused from FE based on their CLEP scores (CLEP Group). Advanced Placement students also participated in the study. From the data, inferences were made that (1) the CLEP had been accurately applied at Utah State University, and (2) the CLEP can validly be used to excuse Utah State University students from FE.
TL;DR: This paper investigated the relationship of library skills, study habits and attitudes, and sex to the academic achievement of college freshmen and found that library skills appeared to be valid for forecasting college success.
Abstract: This study investigated the relationship of library skills, study habits and attitudes, and sex to the academic achievement of college freshmen The multiple regression equation was used to determine the relationships The Library Orientation Test appeared to be valid for forecasting college success
TL;DR: In this paper, a modification of Pearson's fourfold point correlation possessing always-attainable limits of ± 1 and intermediate values operationally interpretable in terms of proporti...
Abstract: Formulas are presented for a modification of Pearson's fourfold point correlation possessing always-attainable limits of ± 1 and intermediate values operationally interpretable in terms of proporti...
TL;DR: In this article, the authors study whether the amount of information and kind of information available to the judges affect the consensus among judges, and two experiments were performed, where the results showed that the information and the kind available to judges did not affect the judges' decisions.
Abstract: The present research was designed to study whether amount of information and kind of information available to the judges affect the consensus among judges. Two experiments were performed, where the...