Criterion Referenced Factor Analysis (CRFA): Method and Illustration

2021 ◽  
Author(s):  
Alvah Bittner
Keyword(s):  
Factor Analysis ◽  
Energy Use ◽  
Lifestyle Factor ◽  
Factor Scores ◽  
Performance Factors ◽  
Primary Model ◽  
Criterion Referenced ◽  
The Stability ◽  
Criterion Variables ◽  
Variance Explained

CRFA is a valid method for evaluating relationships between criteria and “factors'' initially identified from both the predictor and the criterion variables. Among others, it may be applied to classical problems involving: 1) Changes in complex task ability requirements as a function of practice, 2) Impacts of environmental stressors on personality or performance factors overtime, or 3) Residential Lifestyle Factor Impacts on Energy-Use (as herein). CRFA differs from traditional battery developments in its: (a) Initial inclusion of both criterion and predictor variables for factor identifications, but (b) Exclusion of criterion in the ultimate calculation of factor-scores. This avoids the vexing confounding of criterion variance in factor score estimates, and ultimately provides for unconfounded analyses of criterion and factor relationships. A “Big-Data'' illustration of CRFA is presented that highlights the stability of model results for independent samples across years. The primary model of interest built upon a USA-representative survey (N = 2,165) sample of 17 variables adapted from RECS-2005 (USEIA, 2019). These included16 lifestyle-related and an annual energy use criterion (i.e., LNKWH, Ln-transformed annual KiloWatt Hours). Unweighted least squares (ULS) factor analysis revealed a 5- Lifestyle factor solution that accounted for 45.5% of the total variation in the 17-variable set and 45.3% of the 16 less LNKWH. “Lifestyle” factor predictions – subsequently derived by CRFA less LNKWH– are found to be remarkably stable when compared to a similar sample taken 4-years earlier (RECS-2001). Specifically, (1) the proportions of LNKWH variance explained with lifestyle factor scores alone are nearly identical across the 4-year gap (2005 R2 = 0.42- and 2001 R2 = 0.38; ps <10-10), (2) these increased after external additions of household characteristics (R2 = 0.55 both fore- and back-casting; ps <10-15), and model B-weights were near identical. CRFA is strongly recommended for valid evaluations of relationships between criteria and predictor-based factor-scores, where factor characterizations are initially derived from both predictor and criterion variables.

scholarly journals Reliability, comparative validity and stability of dietary patterns derived from an FFQ in the Tehran Lipid and Glucose Study

2012 ◽  
Vol 108 (6) ◽  
pp. 1109-1117 ◽  
Author(s):  
Golaleh Asghari ◽  
Arezoo Rezazadeh ◽  
Firoozeh Hosseini-Esfahani ◽  
Yadollah Mehrabi ◽  
Parvin Mirmiran ◽  
...  
Keyword(s):  
Factor Analysis ◽  
Dietary Patterns ◽  
Reliability And Validity ◽  
Factor Scores ◽  
Limits Of Agreement ◽  
The Third ◽  
The Mean ◽  
The Difference ◽  
The Stability ◽  
Traditional Pattern

The aim of the present study was to assess the reliability, comparative validity and stability of dietary patterns defined by factor analysis for participants of the Tehran Lipid and Glucose Study. A total of 132 subjects, aged ≥ 20 years, completed a 168-item FFQ (FFQ1, FFQ2) twice, with a 14-month interval. Over this duration, twelve dietary recalls (DR) were collected each month. To assess the stability of the FFQ, participants completed the third FFQ (FFQ3) after 8 years. Following these, two dietary patterns – the ‘Iranian Traditional’ and the ‘Western’ – were derived from FFQ1 and FFQ2 and the mean of DR (mDR); and three dietary patterns were identified from FFQ3: the ‘Iranian Traditional’, the ‘Western’ and the ‘Combined’. The reliability correlations between factor scores of the two FFQ were 0·72 for the Iranian Traditional and 0·80 for the Western pattern; corrected month-to-month variations of DR correlations between the FFQ2 and mDR were 0·48 for the first and 0·75 for the second pattern. The 95 % limits of agreement for the difference between factor scores obtained from FFQ2 and mDR lay between − 1·58 and +1·58 for the Iranian Traditional and between − 1·33 and +1·33 for the Western pattern. The intra-class correlations between FFQ2 and FFQ3 were − 0·09 (P = 0·653) and 0·49 (P <0·001) for the ‘Iranian Traditional’ and the ‘Western’, respectively. These data indicate reasonable reliability and validity of the dietary patterns defined by factor analysis. Although the Western pattern was found to be fairly stable, the Iranian Traditional pattern was mostly unstable over the 8 years of the study period.

The Structure Among Measures of Personality, Social Attitudes, Values, and Social Norms

2007 ◽  
Vol 28 (4) ◽  
pp. 240-251 ◽  
Author(s):  
Lazar Stankov
Keyword(s):  
Factor Analysis ◽  
Individual Differences ◽  
Social Norms ◽  
Social Interactions ◽  
Correlation Matrix ◽  
Social Attitudes ◽  
Group Differences ◽  
Factor Scores ◽  
Ethnic Group Differences ◽  
Inside Out

Abstract. This paper presents the results of a study that employed measures of personality, social attitudes, values, and social norms that have been the focus of recent research in individual differences. These measures were given to a sample of participants (N = 1,255) who were enrolled at 25 US colleges and universities. Factor analysis of the correlation matrix produced four factors. Three of these factors corresponded to the domains of Personality/Amoral Social Attitudes, Values, and Social Norms; one factor, Conservatism, cut across the domains. Cognitive ability showed negative correlation with conservatism and amoral social attitudes. The study also examined gender and ethnic group differences on factor scores. The overall interpretation of the findings is consistent with the inside-out view of human social interactions.

Relation between Number of Subjects and Homogeneity of the Scale in Factor Analytic Studies

1997 ◽  
Vol 85 (3_suppl) ◽  
pp. 1168-1170
Author(s):  
S. M. S. Ahmed ◽  
André Michon
Keyword(s):  
Factor Analysis ◽  
Factor Analytic ◽  
Variance Explained

This paper describes a factor analysis of the responses of 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, or 160 subjects. The result shows that homogeneous scales need fewer subjects than heterogeneous scales for stable results in terms of the number of extracted factors and percentage of variance explained.

Factor Analysis and Reliability of the Movement Imagery Questionnaire

1994 ◽  
Vol 78 (3_suppl) ◽  
pp. 1323-1328 ◽  
Author(s):  
Francisco Atienza ◽  
Isabel Balaguer ◽  
Maria Luisa Garcia-Merita
Keyword(s):  
Factor Analysis ◽  
Factor Structure ◽  
Self Report ◽  
Factor Scores ◽  
Men And Women ◽  
Movement Imagery ◽  
Estimate Reliability ◽  
Kinesthetic Imagery

The purpose of this work was to analyze the factor structure, estimate reliability of the Movement Imagery Questionnaire of Hall and Pongrac, and examine differences between men and women on factor scores. The results for 63 men and 47 women supported the bifactorial structure and reliability of this self-report and its adequacy in comparisons of visual and kinesthetic imagery scores.

Factor Analysis of the Stability of Self Scale

1980 ◽  
Vol 47 (3_suppl) ◽  
pp. 1160-1162 ◽  
Author(s):  
Stephen L. Franzoi ◽  
Benjamin J. Reddish
Keyword(s):  
Factor Analysis ◽  
Factor Structure ◽  
Principal Components ◽  
Analysis Data ◽  
Factor Solution ◽  
The Stability

The factor structure of Rosenberg's Stability of Self Scale (1965) was investigated via principal components factor analysis. Data from 92 male and 171 female undergraduates yielded a one-factor solution, supporting Rosenberg's contention that the scale is unidimensional.

Validation of the Beliefs of Physical Activity among Clergy (B-PAC) Instrument

2017 ◽  
Vol 32 (2) ◽  
Author(s):  
Shannon Gwin ◽  
Paul Branscum ◽  
E. Laurette Taylor
Keyword(s):  
Physical Activity ◽  
Factor Analysis ◽  
Construct Validity ◽  
Psychometric Properties ◽  
Internal Consistency ◽  
Internal Consistency Reliability ◽  
Retest Reliability ◽  
Reliable Instrument ◽  
The Stability ◽  
Test Retest Reliability

The purpose of this study was to create a valid and reliable instrument to evaluate theory-basedbeliefs towards physical activity among clergy members. Data were collected from 174 clergy that par-ticipated in a 15-item online and paper-based survey. Psychometric properties of the instrument includedconfirmatory factor analysis (construct validity), and cronbach’s alpha (internal consistency reliability).In addition, the stability (test-retest reliability) of each subscale was evaluated with a sub-sample of 30participants. Results show the instrument was both valid and reliable, and will be useful in future studiestargeting this population. Future implications are discussed.

scholarly journals Enhancement the stability of power system using optimal location of FACTS devices

2020 ◽  
Vol 18 (2) ◽  
pp. 648
Author(s):  
Ali Najim Abdullah ◽  
Ahmed Majeed Ghadhban ◽  
Hayder Salim Hameed ◽  
Husham Idan Hussein
Keyword(s):  
Power Network ◽  
Performance Factors ◽  
Facts Devices ◽  
Clearing Time ◽  
Thyristor Controlled Series Capacitor ◽  
Overall Performance ◽  
Set Up ◽  
The Stability ◽  
And Control ◽  
Better Than

<p><span>This paper proposes a steady-state of the Static Var Compensator (SVC) &amp; Thyristor Controlled Series Capacitor (TCSC) set up for enhancing the damping overall performance and growing the integral clearing time (CCT) of a power network. The indispensable clearing time is carried out through increasing the time fault interval until the gadget loses stability. Increasing the CCT can be contribute to reliability of the safety gadget, decrease the protection machine ranking and cost. In order to attain most enhancement of machine stability via optimizing location, sizing and control modes of SVC and TCSC. Models and methodology for putting and designing shunt FACT’s units SVC (injected reactive strength Q) and series FACT’s devices TCSC (chose capacitive region) are examined in a 6-bus system. Performance factors are described to show validation of SVC and TCSC on extraordinary conditions. It is proven that the SVC is better than TCSC. </span></p>

scholarly journals Adaptasi Sanctification of Marriage Questionnaire: Versi Indonesia untuk Masyarakat Muslim

2021 ◽  
Vol 26 (1) ◽  
pp. 217-232
Author(s):  
Hepi Wahyuningsih ◽  
Dyna Rahayu Suci Pertiwi
Keyword(s):  
Factor Analysis ◽  
Confirmatory Factor Analysis ◽  
Construct Validity ◽  
Exploratory Factor Analysis ◽  
Factor Structure ◽  
Structure Stability ◽  
Validity And Reliability ◽  
Confirmatory Factor ◽  
The Stability ◽  
Composite Reliability

This study aims to adapt the Sanctification of Marriage Questionnaire for Muslims inIndonesia. Adaptation of the Sanctification of Marriage Questionnaire is carried out throughthe stages: translation, providing evidence of construct validity and reliability. Evidence of construct validity was carried out by exploratory factor analysis followed by MGCFA (Multi-Group Confirmatory factor Analysis). In this study, we used a composite reliability. Subjects to reveal the factor structure of sanctification of marriage were 160 married individuals, while the subjects to test the stability of factor structure consisted of 102 husbands and 111 wives. The result of exploratory factor analysis shows that the construct of sanctification of marriage has three factors / dimensions, namely: belief, perceived sacred qualities and manifestation of God. The structure stability of sanctification of marriage was then empirically tested by MGCFA. The results of MGCFA showed that the three factors / dimensions of sanctification of marriage proved stable. The composite reliability coefficient of the Sanctification of Marriage Questionnaire was in a good category. Further research can be carried out to provide evidence of construct validity with predictive validity and concurrent validity of the Sanctification of Marriage Questionnaire. Limitations in this study are discussed further.Keywords: exploratory factor analysis, multi-group confirmatory factor analysis, muslim,sanctification of marriage, scale adaptation

scholarly journals Validity and Reliability Study of the Scale for Determining the Civic-mindedness Levels of Teaching Staff

2017 ◽  
Vol 5 (4) ◽  
pp. 44
Author(s):  
Rüştü Yeşil
Keyword(s):  
Factor Analysis ◽  
Correlation Coefficients ◽  
Teaching Staff ◽  
Validity And Reliability ◽  
Cronbach’S Alpha ◽  
Cronbach's Alpha ◽  
Bartlett Test ◽  
Development Participation ◽  
The Stability ◽  
Civic Mindedness

use after also being checked by linguists. The validity analysis of the scale for the data collected was performed with exploratory factor analysis and item-total correlation tests, while the property of reliability was determined using the Cronbach’s alpha internal consistency coefficient and the stability test was carried out by determining the relationship between two applications conducted at an interval of the five weeks. The scale, which is called the “Scale for Determining the Civic-Mindedness Levels of Individuals” is a five-step Likert-type scale and consists of 27 items that can be collected under three factors. The factor names are “Openness to Criticism/Development”, “Participation/Activeness” and “Lack of Prejudice/Flexibility”. The KMO value of the scale was 0.956; and the Bartlett Test values were x2=11001.719; sd=351; p<0.000. Items in the scale accounted for 56.619% of the total variance. As a result of the confirmatory factor analysis, the χ2 value was 808.07 and the degree of freedom was 321. Χ2/df is 2.51. The fit indices of the scale were determined as RMSEA=0.067; S-RMR=0.049; NFI=0.97. The item-total corrected correlation coefficients of the items in the scale varied between 0.40 and 0.703 (p<.01). The reliability coefficient of the scale was Cronbach’s alpha at 0.954 and the stability coefficients of the items were between 0.496 and 0.674 (p<,01).

Sign in / Sign up

Export Citation Format

Share Document