Determining the Hierarchical Structure of a Multidimensional Body of Information

1971 ◽  
Vol 32 (3) ◽  
pp. 735-746 ◽  
Author(s):  
Albert Zavala
Keyword(s):  
Factor Analysis ◽  
Hierarchical Structure ◽  
Principal Components ◽  
Principal Axis ◽  
Multidimensional Measurement ◽  
Graphic Form ◽  
Two Factors ◽  
The Hierarchical Structure ◽  
Largest Eigenvalues

A method for extracting the hierarchical structure of a body of information is described. The method uses factor analysis to extract the principal components of a multidimensional measurement space. The principal axis solution of the factor analysis is rotated, starting with the two factors having the largest eigenvalues, and in successive rotations, adding facors with the highest eigenvalue from the remaining unrotated factors. The results are then presented in graphic form. The method is called rotation to hierarchical structure (Rotohist) and uses a single computer run for the analysis.

Perceiving Hierarchical Structures in Nonrepresentational Paintings

1998 ◽  
Vol 16 (1) ◽  
pp. 59-70 ◽  
Author(s):  
Tsion Avital ◽  
Gerald C. Cupchik
Keyword(s):  
Factor Analysis ◽  
Multidimensional Scaling ◽  
Hierarchical Structure ◽  
Hierarchical Structures ◽  
Exploratory Activity ◽  
Affective Responses ◽  
Hierarchical Complexity ◽  
The Hierarchical Structure ◽  
Relative Separation ◽  
Dimension 2

A series of four experiments were conducted to examine viewer perceptions of three sets of five nonrepresentational paintings. Increased complexity was embedded in the hierarchical structure of each set by carefully selecting colors and ordering them in each successive painting according to certain rules of transformation which created hierarchies. Experiment 1 supported the hypothesis that subjects would discern the hierarchical complexity underlying the sets of paintings. In Experiment 2 viewers rated the paintings on collative (complexity, disorder) and affective (pleasing, interesting, tension, and power) scales, and a factor analysis revealed that affective ratings were tied to complexity (Factor 1) but not to disorder (Factor 2). In Experiment 3, a measure of exploratory activity (free looking time) was correlated with complexity (Factor 1) but not with disorder (Factor 2). Multidimensional scaling was used in Experiment 4 to examine perceptions of the paintings seen in pairs. Dimension 1 contrasted Soft with Hard-Edged paintings, while Dimension 2 reflected the relative separation of figure from ground in these paintings. Together these results show that untrained viewers can discern hierarchical complexity in paintings and that this quality stimulates affective responses and exploratory activity.

scholarly journals Validation of Academic Delay of Gratification Scale among Indian Professional Courses Students

2017 ◽  
Vol 4 (2) ◽  
Author(s):  
Rajib Chakraborty
Keyword(s):  
Factor Analysis ◽  
Principal Axis ◽  
Delay Of Gratification ◽  
P Value ◽  
Education Society ◽  
Education Professional ◽  
Two Factors ◽  
Fit Index ◽  
Academic Delay ◽  
Academic Delay Of Gratification

The present study is an attempt to conduct factor analysis of the Academic Delay of Gratification Scale (ADOGS) for college students, with 10 items, prepared by Bembenutty and Karabenick (1998), on Indian professional courses students. 461 students (256 boys and 205 girls) from engineering, pharmacy, law and education professional courses of Sultan Ul Uloom Education Society, Hyderabad, voluntarily participated in the study, out of which 336 students (190 boys and 146 girls) were part of exploratory factor analysis. With the help of SPSS Statistics Ver.23, Principal Axis Factor extraction method and Varimax rotation, two factors were extracted. Monte Carlo PCA Parallel Analysis was used to settle for one factor explaining 16% variance. The reliability of the instrument using Cronbach’s Alpha was found to be 0.715. SPSS Amos Ver. 23 was used to confirm the factor structure and establish within-network construct validity of the instrument using Fit index tests like Chi test p value, DF, CMIN/DF, TLI, CFI, IFI, NFI,RMR and RMSEA from the data of 125 students (66 boys and 59 girls), followed by between network validity based on construct validation approach using Pearson’s product moment correlation the data of 136 students (100 boys and 36 girls) measuring their academic delay of gratification and emotional intelligence. There were sufficient evidences to establish that this instrument in its present form can be administered on Indian urban students for the measurement of academic delay of gratification.

Factor Structure, Reliability, and Validity of the Death Attitude Profile-Revised

2000 ◽  
Vol 40 (3) ◽  
pp. 453-463 ◽  
Author(s):  
Richard Clements ◽  
Linda A. Rooda
Keyword(s):  
Factor Analysis ◽  
Factor Structure ◽  
Internal Consistency ◽  
Principal Components ◽  
Concurrent Validity ◽  
Reliability And Validity ◽  
Fear Of Death ◽  
Hospice Nurses ◽  
Structure Reliability ◽  
Two Factors

The Present Study Examined The Factor Structure, reliability, and validity of the Death Attitude Profile-Revised (DAP-R; Wong, Reker, & Gesser, 1994) using a sample of 403 hospital and hospice nurses. A principal-components factor analysis of the DAP-R indicated that the DAP-R may consist of six factors instead of the five originally reported by Wong et al. The first four factors reported by Wong et al., which correspond to the subscales that they labeled Fear of Death, Death Avoidance, Approach Acceptance, and Escape Acceptance, were replicated in the present study, and these subscales were found to have acceptable levels of internal consistency and to possess some degree of concurrent validity. However, the items which loaded on the fifth factor in Wong et al.‘s study (their “Neutral Acceptance” subscale) were split across two factors in the present study, suggesting that this subscale may not be measuring a unitary construct.

AUTHORITARIANISM REVISITED: EVIDENCE FOR AN AGGRESSION FACTOR

1981 ◽  
Vol 9 (2) ◽  
pp. 147-153 ◽  
Author(s):  
David Raden
Keyword(s):  
Factor Analysis ◽  
Vietnam War ◽  
Principal Components ◽  
Short Version ◽  
Two Factors ◽  
The Vietnam War

A principal components factor analysis was performed on the scores of 245 undergraduates to a short version of the F Scale and measures of prejudice, attitude toward welfare, toleration of political deviance, punitiveness toward criminals, and support of the Vietnam War. The analysis produced two factors. One was an authoritarian aggression factor which was consistent with the Berkeley levels of personality approach and previous factorial research. All of the measures except the welfare items had substantial loadings on this factor. The second was an attitude toward welfare factor which appeared to be unrelated to authoritarianism.

Dimensions of Rosenburg's Self-Esteem Scale

1976 ◽  
Vol 38 (2) ◽  
pp. 583-584 ◽  
Author(s):  
Wayne E. Hensley ◽  
Mary K. Roberts
Keyword(s):  
Factor Analysis ◽  
Principal Components ◽  
Analysis Data ◽  
Self Esteem ◽  
Factor Solution ◽  
Response Set ◽  
Two Factors

The dimensions of Rosenburg's scale of self-esteem (1965) were investigated via principal components and oblique factor analysis. Data from 479 students in a basic speech course yielded a two-factor solution. As the two factors appeared to identify only a response set, it was concluded the scale was unidimensional.

scholarly journals Principal Components Analysis Utility in the Livestock Field

2016 ◽  
Vol 73 (2) ◽  
pp. 251
Author(s):  
Ancuta Simona Rotaru ◽  
Ioana Pop ◽  
Anamaria Vatca ◽  
Luisa Andronie
Keyword(s):  
Factor Analysis ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Latent Variables ◽  
Principal Component ◽  
The Other ◽  
Data Sets ◽  
Method Factor ◽  
Two Factors ◽  
Components Analysis

Principal Component Analysis is a method factor - factor analysis - and is used to reduce data complexity by replacingmassive data sets by smaller sets. It is also used to highlight the way in which the variables are correlated with eachother and to determining the (less)latent variableswhich are behind the (more)measured variables. These latent variables are called factors, hence the name of the methodi.e. factor analysis. Our paper shows the applicability of Principal Components Analysis (PCA) in livestock area of study by carrying out a researchon some physiological characteristics in the case of tencow breeds.By using PCA only two factors have been preserved, concentrating over 80% of their information from the four variables in question, one factor concentrating weight and height and the other factor concentrating trunk circumference and weight at calving, respectively.

Factor Analytic Support for Psychosocial and Vocational Mentoring Functions

1985 ◽  
Vol 57 (2) ◽  
pp. 627-630 ◽  
Author(s):  
Melanie R. Schockett ◽  
Marilyn Haring-Hidore
Keyword(s):  
College Students ◽  
Factor Analysis ◽  
Principal Axis ◽  
Prior Work ◽  
Oblique Rotation ◽  
Factor Analytic ◽  
Mentoring Functions ◽  
Two Factors ◽  
Principal Axis Factor Analysis ◽  
Principal Axis Factor

Eight 50-word vignettes which portrayed either psychosocial or vocational mentoring functions were presented to 144 college students who rated the desirability of each function on a scale of 1 to 7. A principal axis factor analysis with oblique rotation yielded two factors, one on which the psychosocial functions loaded more heavily (and which accounted for 33.4% of the variance) and one on which the vocational functions loaded more heavily (and which accounted for an additional 5.9% of the variance). The results may help researchers formulate different questions about mentoring than the basic questions which have guided prior work.

Toward a More Perfect Conceptualization of Perfectionism: An Exploratory Factor Analysis in Undergraduate College Students

Assessment ◽  
2020 ◽  
pp. 107319112097685
Author(s):  
Anthony Robinson ◽  
Sara Stasik-O’Brien ◽  
Matthew Calamia
Keyword(s):  
College Students ◽  
Factor Analysis ◽  
Exploratory Factor Analysis ◽  
Factor Structure ◽  
Hierarchical Structure ◽  
Structural Equation ◽  
Equation Modeling ◽  
Five Dimensions ◽  
Evaluative Concerns ◽  
The Hierarchical Structure

Previous investigations on the factor structure of perfectionism have largely focused on the Frost Multidimensional Perfectionism Scale and the Multidimensional Perfectionism Scale. The current study aimed to identify the underlying factor structure of perfectionism, based on several widely used measures, and to examine how these factors related to psychopathology and personality broadly. College students ( N = 598) completed several measures of perfectionism and broadband measures of psychopathology and personality. Exploratory structural equation modeling (ESEM) was conducted to examine the hierarchical structure of perfectionism followed by exploratory factor analysis. The hierarchical structure examined provides a framework for understanding the relationship between models of perfectionism at different levels of the hierarchy. The exploratory factor analysis revealed five dimensions of perfectionism: Achievement Striving, Evaluative Concerns, Expectations From Others, Narcissistic Perfectionism, and Organization. These dimensions were associated with psychopathology to differing degrees and were differentially related to personality. These results support using a multidimensional perspective to understand perfectionism.

A Further Validation of the Children's Behavioral Classification Project Inventory

1997 ◽  
Vol 81 (1) ◽  
pp. 259-271
Author(s):  
Ralph Mason Dreger
Keyword(s):  
Factor Analysis ◽  
Confirmatory Factor Analysis ◽  
Phase I ◽  
Principal Components ◽  
Two Samples ◽  
Confirmatory Factor ◽  
Two Factors ◽  
Behavioral Classification ◽  
Components Analysis ◽  
Classification Project

To add evidence of the validity of the Children's Behavioral Classification Inventory, the responses of parents and teachers were compared on a set of 110 items of the inventory which describe behaviors equally observable to both groups. The two sets of data were subjected in Phase I to principal components analysis to extract two factors in each case which were compared by means of the Ahmavaara transformation and found to be highly comparable. In Phase II, predictions were made from factor weights of 36 items measuring six factors in the original standardization of the inventory to both sets of respondents' data by means of confirmatory factor analysis. The formal indices of comparability were not generally in acceptable ranges; however, substantively the six factors were definitely replicated in the two samples.

Sign in / Sign up

Export Citation Format

Share Document