Some comparisons of the multiple-factor and the bi-factor methods of analysis

Bi-factor and multiple-factor analyses of the same data are compared in two respects. First, two criteria are suggested for determining when the factorization is adequate. This problem being more acute for the centroid method than for the bi-factor method, the latter is used primarily for comparison only. It is shown also that the omission from the simple structure of entries smaller than .10 yields a pattern which is a poorer fit to the original correlations than is the bi-factor pattern. Second, the second-order general factor obtained from the intercorrelations of the primaries is found to be highly correlated with the general factor of the bi-factor pattern.     

The bifactor structure and the “dark nomological network” of the State Self-Esteem Scale

The State Self-Esteem Scale (SSES) measures transient feelings of self-worth. The SSES has been hypothesized to possess a number of latent structures, ranging from one to three factors. The present study compared these putative structures along with a newly hypothesized bifactor structure (i.e., one global factor, three subfactors). Results offered greatest support for the bifactor model. A secondary goal was to further assess the nomological network surrounding state self-esteem by examining correlations involving an expanded measure of basic personality (i.e., the HEXACO), Dark Triad traits, and sexual attitudes and behaviors. In general, these correlations were consistent with the theoretical portrait of state self-esteem and were also consistent with correlations involving trait-level self-esteem. Most notably, however, scores on the SSES consistently correlated negatively with measures of the Dark Triad traits, suggesting a possible theoretical distinction between state- and trait-level self-esteem.     

The measurement of speed in motor performance

When the centroid method of factor analysis was applied to two sets of data on athletic performances, three significant factors emerged: strength, velocity, and dead weight. Scores on this speed factor were predicted by the multiple regression technique, the factor loadings on the speed factor being used as the criterion correlations, and these predicted scores were correlated with each of the other variables. When the original tables, augmented by the new speed variable, were refactored, the computed speed factor fell on the speed axis as a primary trait. It is thus shown that it is possible to isolate and measure a factor which appears in variables under consideration only as a compound.Much of the expense of the statistical computations connected with this study was financed by a grant from the Carnegie Foundation for the Advancement of Teaching.     

The relation between factor loadings and biserial correlations in item analysis

The first centroid factor loadings obtained from various interitem relations are compared with item discrimination indices commonly used in item analysis. Depending upon what type of matrix is factored, the factor loadings are shown to be related to point biserial and biserial correlations.     

EPQ correlates of the delusions-symptoms-states inventory

Ninety-seven Day Hospital patients were asked to complete a set of questionnaires, including the Eysenck Personality Questionnaire and the Delusions-Symptoms-States Inventory of Bedford and Foulds. This paper studies the resulting correlations between the variables measured by these two inventories. No correlations were found between the Extroversion-Introversion dimension and the DSSI categories, and likewise for the Lie Scale. However, Neuroticism showed significant correlations with dysthymic states, neurotic symptoms, and integrated delusions, whilst Psychoticism correlated significantly with the delusional components only. Although this finding could be used to support certain theories about the relationship between these variables, certain theoretical difficulties remain and, in the case of this data, certain artefactual elements may have been influential.     

Music ability

Two batteries of music tests were factored by the centroid method. From each battery three oblique factors were extracted and in each case were tentatively identified as tonal sensitivity, retentivity (memory for elements), and memory for form. The correlations of the music tests of one battery with subtests of Cattell's intelligence test and with tests of a literary nature are also reported.Karlin, J. E. A multiple factor analysis of musicality. M. A. thesis, University of Cape Town, 1939.Drake, R. M. A factorial analysis of music tests by the Spearman tetrad-difference technique.J. Musicology, 1939, 1, 1.     

To Balance or not to Balance: Confirmatory Factor Analysis of the Affect-Balance Scale

This study examined the psychometric quality of the Affect-Balance Scale (ABS) (Bradburn, 1969) using data collected from 292 middle-aged and older adults, living independently. The dimensionality of the scale was examined, the quality of individual items was tested, and the validity of the ABS was studied. Using a tetrachoric correlation matrix with the robust weighted least squares (WLSMV) estimation method of the Mplus program, we found that two moderately correlated (r = -0.37) constructs are needed to adequately account for the pattern of item scores in the ABS. Two of the 10 ABS items were found to be problematic. When raw sum scores were used in analysis, the correlation between the positive-affect and the negative-affect subscales was lower (r = -0.17), indicating that random and nonrandom measurement error masked the relationship between the two. While affect-balance correlated substantially with five criterion well-being measures, the negative-affect subscale (which constitutes half of the ABS) had a similar pattern of correlations, with only slightly lower magnitude. The theoretical construct of nobreak 'balance' is also questioned. The 'balance' scoring method (subtracting the negative-affect subscale score from the positive-affect subscale score) nets exactly the same score as does summing scores from both subscales together. Accordingly, the summed scores have the very same correlations with other variables as do the balance scores.     

A general factor of personality,social desirability,cognitive ability,and the survey of work styles in an employment selection setting

How a general factor of personality (GFP) correlated with employment screening measures in an applied setting was examined. Participants were 540 adult insurance sales job applicants who completed scales from two personality measures, the five scales from the Survey of Work Styles (SWS), an intelligence measure, and a social desirability scale. A joint factor analysis of the personality questionnaires produced four first order factors. A single GFP was also extracted. Strong correlations were found between some of the personality factors and the SWS scales. Strong significant correlations were found between the GFP and three of the four personality factors with social desirability. Neither the GFP nor the personality factors correlated significantly with cognitive abilities.     

Phased mirror tracing outcomes correlate with several hemisphericity measures

Recently, subjects, separated into two large groups by the Dichotic Deafness Test (DDT), a new brain laterality measure. These were significantly correlated with groups separated by two preference-based hemisphericity-type questionnaires, the Preference Questionnaire (PrefQ) and Polarity Questionnaire (PolQ). Here, Mirror-Tracing, another potential biophysical measure of hemisphericity earlier reported to be weakly correlated with laterality, was tested using 171 subjects, the DDT, and both questionnaires. No correlations between the DDT, PrefQ, and PolQ separation methods and Mirror Tracing outcomes were found until individuals identified as having left brain affect were removed from the population. Then, robust correlations appeared for the remaining right-affect subjects alone (n=82). These correlations became even higher when the left brain affect subjects that had been removed (n=89) were "phase corrected" from a contralateral to an ipsilateral connectivity for motor dominance and then returned to the sample (n=171). These Phased Mirror-Tracing (PMT) outcomes were also significantly correlated with 10 of the 11 statements of the PolQ. Thus, PMT joins the DDT as a second performance-based measure of laterality whose outcomes significantly correlated with those of preference-based hemisphericity questionnaires.     

The Life Attitudes Schedule Short Form: An Abbreviated Measure of Life-Enhancing and Life-Threatening Behaviors in Adolescents

An abbreviated version of the Life Attitudes Schedule (LAS) was developed, consisting of 24 items, each representing one cell of the original LAS theoretical matrix (4 content categories × 2 behavior types × 2 valence). Items were retained on the basis of high correlations with LAS total score and low correlations with gender. Psychometric properties of the LAS Short Form were robust and the Short Form total score correlated .93 with the original LAS total score. As with the original LAS, boys reported more injury-related behaviors than girls. Future research and clinical directions are suggested.     

A simple method of factor analysis

A simple method for extracting correlated factors simultaneously is described. The method is based on the idea that the centroid pattern coefficients for the sections of unit rank of the complete matrix may be interpreted as structure values for the entire matrix. Only the routine centroid average process is required.     

Individual Differences In Intra-Individual Variability

For each of 75 Ss several estimates of intra-individual variations were calculated for each of 4 motor skills. The reliability of intra-individual variation for these data, estimated from Pearson productmoment correlations, ranged from r = .31 to r = .51 (in all cases p < .05). It was also found that in 3 of the 4 skills, intra-individual variation correlated significantly (r = .36, .54, .55) with mean performance level. Second order partial correlations, holding constant the effect of mean performance level, were then used to estimate the reliability of intravariation. These correlations were statistically significant and ranged from r = .27 to r = .34. When correlations of intra-individual variation were calculated among the four skills it was demonstrated that intra-individual variation was approximately 95 to 100% task specific.     

Constructive Thinking and Elevated Ratings of Self in Interpersonal Groups

Probing Taylor and Brown's (1988) connection of mental health with favorably slanted self-evaluations, responses to Epstein's (1987) Constructive Thinking Inventory (CTI) were correlated with ratings of interpersonal behavior. Several weeks after completing the CTI, 103 small-group members rated themselves and each other for self-accepting and other-accepting conduct. Separately for each acceptance scale, eight CTI measures were correlated with differences of self-ratings (S) from the mean rating individuals' received (R) from others, the mean rating each gave (G) to these others, and all components. Agreeing substantially, indicators S and R also correlated with the CTI measures similarly but in a pattern opposite to G's correlations. Supporting Taylor and Brown, 12 of 16 correlations of CTI measures with intrarater (S – G) differences attained statistical significance (p < .05) unlike any parallel correlation with interrater differences (S – R). Constructive thinking and rating oneself above peers—especially for acceptance of self—consistently correlated positively, suggesting an underlying sense of independence.     

Temporal lobe signs: electroencephalographic validity and enhanced scores in special populations

Internal and external validity tests were completed for an inventory that has been used to infer signs of temporal lobe lability. Strong, positive correlations were reported for a normal (reference) population between the numbers of responses that referred to paranormal experiences (including feelings of a "presence") and separately to religious beliefs and the numbers of spikes per minute within electroencephalographic recordings from the temporal lobe. Numbers of spikes were also correlated with the subjects' scores on the hysteria, schizophrenia, and psychasthenia scales from the MMPI. These clusters of items were not correlated with electrical activity from the occipital lobe (the comparison region). Numbers of responses to control clusters of mundane experiences were not correlated with the temporal lobe measures. A group of student poets scored higher on different subclusters of temporal lobe signs and on the schizophrenia and mania scales of the MMPI than the reference group. For both groups, there were positive correlations between the amount of alpha activity in the temporal lobe only and answers to items such as "hearing inner voices" and "feeling as if things were not real." These results demonstrate that quantitative measures of electrical changes in the temporal lobe are correlated with (or with the report of) specific experiences that are prevalent during surgical or epileptic stimulation of this brain region.     

A comparative study of three methods of rotation

Three methods of rotation (the graphical, the Thurstone analytical, and the direct-rotational) were applied to the matrix of centroid loadings for 35 variables, to determine which method is the most efficient from theoretical and practical standpoints. The direct-rotational method provided the most information for determining the rank of the configuration and was most economical with respect to time required to reach a rotational solution. The analytical method required the least number of judgmental decisions and was the most objective. The graphical method was the most laborious but had a slight advantage with regard to the number of near-zero loadings in the rotational solution.Systems Development Corp.     

Valence band structure of the NiAl–Mo alloy from the photoelectron spectrum

The valence band structures of the NiAl–Mo alloy was investigated by photoelectron spectroscopy. The valence band spectra of the NiAl–Mo alloy was shifted away from the Fermi level so that the Ni-d-band centroid moved to a higher energy by 0.22 eV as Mo was added. A possible explanation lied in the overlap of Ni-d bands in the energy with Mo-d and Al-p bands. The participation of Mo-d bands was correlated with the site preference of Mo in NiAl alloys.     

大学生幽默风格与精神健康关系的初步研究

目的:测试幽默风格量表在中国大学生中的信度和效度,探讨幽默风格与精神健康之间的关系。方法:354名大学生接受幽默风格量表和症状自评量表(SCL-90)的问卷调查,4周后74名大学生重新填写幽默风格量表。结果:幽默风格量表所提出的4个因子结构在中国人的样本中也存在,该量表的信度和效度可接受。中国被试在4个子量表的得分均低于加拿大被试的得分。亲和型幽默、自强型幽默得分与症状自评量表的子量表以及总体症状指数得分全部呈现负相关,而嘲讽型幽默和自贬型幽默得分与症状自评量表的子量表以及总体症状指数得分全部呈现正相关。结论:(1)该量表的初步测试效度和信度可接受,但须结合中国文化作进一步的修订;(2)亲和型和自强型幽默有益于精神健康,但嘲讽型和自贬型幽默有害于精神健康;(3)中国人与加拿大人在幽默风格、幽默对精神健康起作用的方式上存在一定的文化差异。     

The Association between Anxiety and Psychopathy Dimensions in Children

Although several theoretical models posit that low levels of anxiety are a risk factor for psychopathy and antisocial behavior, a number of studies have reported elevated levels of anxiety among antisocial individuals. Nevertheless, most investigators in this literature have not distinguished between fearfulness and trait anxiety or attempted to separate the antisocial lifestyle dimension from the callous and unemotional dimension of psychopathy. In a study of clinically referred children (N = 143), we found that (a) measures of trait anxiety and fearlessness (low fearfulness) exhibited low correlations; (b) conduct problems tended to be positively correlated with trait anxiety, whereas callous and unemotional traits tended to be negatively correlated with trait anxiety; and (c) controlling statistically for the effects of one dimension increased the divergent correlations of the other dimension with both trait anxiety and fearful inhibition. These findings bear potentially important implications for the diagnosis and etiology of psychopathy and antisocial behavior and suggest that distinctions between trait anxiety and fearful inhibition, as well as between the two dimensions of psychopathy, may help to clarify longstanding confusion in this literature.     

Verification of hypothesized factors in one hundred and fifteen objective personality test designs

This paper reports on the third of a series of four experiments using similar concepts and methods for objective personality measurement, and overlapping test batteries. One hundred students were measured with 115 tests. The scores were correlated and factored by a re-iterated multiple group centroid method. The 17 factors thus obtained were rotated toward a clear simple structure. The relation of the rotated factors to earlier ones is indicated, but no extensive interpretation is attempted.     

Individual differences and interrelationships among a select set of cognitive skills

An experiment was conducted to investigate individual differences and interrelationships in performance on three short-term memory processing and visual processing tasks. Parameters of models for these tasks were correlated. High correlations (.97 and .83) were obtained for some intertask parameters. indicating that elemental component processes for different tasks can be identified that are similar or highly related. Psychometric measures (SATM and SATV) were also correlated with the information processing model parameters. High multiple correlations of SATV and SATM were obtained using model parameters as predictors. when the data were analyzed separately for female and male subjects. The results are suggestive of sex differences in the interrelationships of the cognitive processes under investigation.