Determining the Number of Factors When Population Models Can Be Closely Approximated by Parsimonious Models

2021 ◽  
pp. 001316442199283
Author(s):  
Yan Xia
Keyword(s):  
Factor Model ◽  
Population Level ◽  
Parallel Analysis ◽  
Model Data ◽  
Behavioral Studies ◽  
Number Of Factors ◽  
Parsimonious Models ◽  
Parsimonious Model ◽  
Fit Index ◽  
Tucker Lewis Index

Despite the existence of many methods for determining the number of factors, none outperforms the others under every condition. This study compares traditional parallel analysis (TPA), revised parallel analysis (RPA), Kaiser’s rule, minimum average partial, sequential χ2, and sequential root mean square error of approximation, comparative fit index, and Tucker–Lewis index under a realistic scenario in behavioral studies, where researchers employ a closing–fitting parsimonious model with K factors to approximate a population model, leading to a trivial model-data misfit. Results show that while traditional and RPA both stand out when zero population-level misfits exist, the accuracy of RPA substantially deteriorates when a K-factor model can closely approximate the population. TPA is the least sensitive to trivial misfits and results in the highest accuracy across most simulation conditions. This study suggests the use of TPA for the investigated models. Results also imply that RPA requires further revision to accommodate a degree of model–data misfit that can be tolerated.

Psychometric Testing of the Modified Reminiscence Functions Scale

2014 ◽  
Vol 22 (3) ◽  
pp. 500-510 ◽  
Author(s):  
Juliette M. Shellman ◽  
Danjie Zhang
Keyword(s):  
Factor Model ◽  
Psychometric Testing ◽  
Community Dwelling ◽  
Black Adults ◽  
Chi Square ◽  
Convenience Sample ◽  
Number Of Factors ◽  
Confirmatory Factor ◽  
Fit Index ◽  
Tucker Lewis Index

Background and Purpose: The Modified Reminiscence Functions Scale (MRFS) measures the patterns and functions of reminiscence. The purpose of this study was to examine the factor structure of the MRFS in a sample of community-dwelling Black adults. Methods: A convenience sample (N= 335) of Black adults from the Northeast completed the 39-item MRFS. Seven- and 8-factor models were evaluated given the uncertainty regarding the number of factors in previous reminiscence research. Results: Confirmatory factor analysis established validity of the 7-factor model (relative chi-square [χ2/df] = 1.9, Tucker-Lewis index [TLI] = .919, comparative fit index [CFI] = .929, root mean square error of approximation [RMSEA] = .05). Reliability of the subscales ranged from .64 to .90. Conclusions: The MRFS is a reliable and valid measure of reminiscence patterns and functions in Black adults with similar characteristics.

scholarly journals Using Fit Statistic Differences to Determine the Optimal Number of Factors to Retain in an Exploratory Factor Analysis

2019 ◽  
Vol 80 (2) ◽  
pp. 217-241 ◽  
Author(s):  
W. Holmes Finch
Keyword(s):  
Factor Analysis ◽  
Exploratory Factor Analysis ◽  
Optimal Number ◽  
Parallel Analysis ◽  
Fit Indices ◽  
Number Of Factors ◽  
Indicator Variables ◽  
Model Fit Indices ◽  
Fit Index ◽  
Normally Distributed

Exploratory factor analysis (EFA) is widely used by researchers in the social sciences to characterize the latent structure underlying a set of observed indicator variables. One of the primary issues that must be resolved when conducting an EFA is determination of the number of factors to retain. There exist a large number of statistical tools designed to address this question, with none being universally optimal across applications. Recently, researchers have investigated the use of model fit indices that are commonly used in the conduct of confirmatory factor analysis to determine the number of factors to retain in EFA. These results have yielded mixed results, appearing to be effective when used in conjunction with normally distributed indicators, but not being as effective for categorical indicators. The purpose of this simulation study was to compare the performance of difference values for several fit indices as a method for identifying the optimal number of factors to retain in an EFA, with parallel analysis, which is one of the most reliable such extant methods. Results of the simulation demonstrated that the use of fit index difference values outperformed parallel analysis for categorical indicators, and for normally distributed indicators when factor loadings were small. Implications of these findings are discussed.

scholarly journals Assessing Women’s Menstruation Concerns and Experiences in Rural India: Development and Validation of a Menstrual Insecurity Measure

2020 ◽  
Vol 17 (10) ◽  
pp. 3468
Author(s):  
Bethany A. Caruso ◽  
Gerard Portela ◽  
Shauna McManus ◽  
Thomas Clasen
Keyword(s):  
Factor Model ◽  
Five Factor Model ◽  
Water Source ◽  
Cross Sectional ◽  
Negative Experiences ◽  
Menstruating Women ◽  
Fit Index ◽  
Post Hoc ◽  
Development And Validation ◽  
Tucker Lewis Index

Qualitative research has documented menstruator’s challenges, particularly in water and sanitation poor environments, but quantitative assessment is limited. We created and validated a culturally-grounded measure of Menstrual Insecurity to assess women’s menstruation-related concerns and negative experiences. With cross-sectional data from 878 menstruating women in rural Odisha, India, we carried out Exploratory (EFA) and Confirmatory (CFA) Factor Analyses to reduce a 40-item pool and identify and confirm the scale factor structure. A 19-item, five factor model best fit the data (EFA: root mean square error of approximation (RMSEA) = 0.027; comparative fit index (CFI) = 0.994; Tucker-Lewis index (TLI) = 0.989; CFA: RMSEA = 0.058; CFI = 0.937; TLI = 0.925). Sub-scales included: Management, Menstrual Cycle Concerns, Symptoms, Restrictions, and Menstruation-Related Bodily Concerns. Those without access to a functional latrine, enclosed bathing space, water source within their compound, or who used reusable cloth had significantly higher overall Menstrual Insecurity scores (greater insecurity) than those with these facilities or using disposable pads. Post-hoc exploratory analysis found that women reporting experiencing tension at menstrual onset or difficulty doing work had significantly higher Menstrual Insecurity scores. This validated tool is useful for measuring Menstrual Insecurity, assessing health inequities and correlates of Menstrual Insecurity, and informing program design.

Number of Factors Decision: Parallel Analysis Is Not the Panacea

2006 ◽  
Author(s):  
Jinyan Fan ◽  
Felix James Lopez ◽  
Jennifer Nieman ◽  
Robert C. Litchfield ◽  
Robert S. Billings
Keyword(s):  
Parallel Analysis ◽  
Number Of Factors

scholarly journals Construct validity and reliability of the generalised anxiety disorder-7 scale in a sample of tuberculosis patients in the Free State Province, South Africa

2021 ◽  
Vol 36 (1) ◽  
Author(s):  
Gladys Kigozi
Keyword(s):  
Anxiety Disorder ◽  
Construct Validity ◽  
Factor Model ◽  
Poor Quality ◽  
Free State ◽  
Generalised Anxiety Disorder ◽  
Validity And Reliability ◽  
Emotional Symptoms ◽  
Convenience Sample ◽  
Fit Index

Background: Generalised anxiety disorder (GAD) frequently occurs amongst patients with tuberculosis (TB) and contributes to poor quality of life and treatment outcomes. This study evaluated the construct validity and reliability of the GAD-7 scale in a sample of patients with TB in the Free State Province.Methods: A pilot study was conducted amongst a convenience sample of 208 adult patients newly diagnosed with drug-susceptible TB attending primary healthcare (PHC) facilities in the Lejweleputswa District in the Free State. A structured interviewer-administered questionnaire comprising social demographic questions and the GAD-7 scale was used. Confirmatory factor analysis was used to investigate the construct validity of the GAD-7 scale. The reliability of the scale was assessed by calculating Cronbach’s alpha.Results: The analysis showed that a modified two-factor (somatic symptoms and cognitive -emotional symptoms) model, in which the items ‘Not being able to stop or control worrying’ and ‘Worrying too much about different things’ were allowed to covary (Comparative Fit Index: 0.996, Tucker–Lewis Index: 0.993, Root Mean Square Error of Approximation: 0.070, 90% confidence interval: 0.032–0.089), fitted the data better than a unidimensional (generalised anxiety) or an unmodified two-factor model. The indicators all showed significant positive factor loadings, with standardised coefficients ranging from 0.719 to 0.873. The Cronbach’s alpha of the scale was 0.86.Conclusion: The modified two-factor structure and high internal consistency respectively provide evidence for construct validity and reliability of the GAD-7 scale for assessing GAD amongst patients with TB. Studies are necessary to assess the performance of this brief scale under routine TB programme conditions in the Free State.

scholarly journals Entropy Fit Indices: New Fit Measures for Assessing the Structure and Dimensionality of Multiple Latent Variables.

2019 ◽  
Author(s):  
Hudson Golino ◽  
Robert Glenn Moulder ◽  
Dingjing Shi ◽  
Alexander P. Christensen ◽  
Luis E. Garrido ◽  
...  
Keyword(s):  
Information Theory ◽  
Quantum Information ◽  
Latent Variables ◽  
Categorical Variables ◽  
Graph Analysis ◽  
Fit Indices ◽  
Latent Factors ◽  
Accurate Identification ◽  
Number Of Factors ◽  
Fit Index

The accurate identification of the content and number of latent factors underlying multivariate data is an important endeavor in many areas of Psychology and related fields. Recently, a new dimensionality assessment technique based on network psychometrics was proposed (Exploratory Graph Analysis, EGA), but a measure to check the fit of the dimensionality structure to the data estimated via EGA is still lacking. Although traditional factor-analytic fit measures are widespread, recent research has identified limitations for their effectiveness in categorical variables. Here, we propose three new fit measures (termed entropy fit indices) that combines information theory, quantum information theory and structural analysis: Entropy Fit Index (EFI), EFI with Von Neumman Entropy (EFI.vn) and Total EFI.vn (TEFI.vn). The first can be estimated in complete datasets using Shannon entropy, while EFI.vn and TEFI.vn can be estimated in correlation matrices using quantum information metrics. We show, through several simulations, that TEFI.vn, EFI.vn and EFI are as accurate or more accurate than traditional fit measures when identifying the number of simulated latent factors. However, in conditions where more factors are extracted than the number of factors simulated, only TEFI.vn presents a very high accuracy. In addition, we provide an applied example that demonstrates how the new fit measures can be used with a real-world dataset, using exploratory graph analysis.

Development, validity and reliability testing the Swedish Ethical Climate Questionnaire

2019 ◽  
Vol 26 (7-8) ◽  
pp. 2482-2493 ◽  
Author(s):  
Catarina Fischer Grönlund ◽  
Anna Söderberg ◽  
Vera Dahlqvist ◽  
Lars Andersson ◽  
Ulf Isaksson
Keyword(s):  
Factor Analysis ◽  
Exploratory Factor Analysis ◽  
Ethical Climate ◽  
Factor Model ◽  
Parallel Analysis ◽  
Validity And Reliability ◽  
Cronbach’S Alpha ◽  
Cronbach's Alpha ◽  
Professional Perspective ◽  
Ethical Climate Questionnaire

Background: An ethical climate has been described as a working climate embracing shared perceptions about morally correct behaviour concerning ethical issues. Various ethical climate questionnaires have been developed and validated for different contexts, but no questionnaire has been found concerning the ethical climate from an inter-professional perspective in a healthcare context. The Swedish Ethical Climate Questionnaire, based on Habermas’ four requirements for a democratic dialogue, attempts to assess and measure the ethical climate at various inter-professional workplaces. This study aimed to present the construction of and to test the psychometric properties of the Swedish Ethical Climate Questionnaire. Method: An expert group of six researchers, skilled in ethics, evaluated the content validity. The questionnaire was tested among 355 healthcare workers at three hospitals in Sweden. A parallel analysis (PA), an exploratory factor analysis and confirmatory factor analysis were performed. Ethical considerations: The participants included in the psychometric analysis were informed about the study, asked to participate in person and informed that they could withdraw at any time without giving any reason. They were also assured of confidentiality in the reporting of the results. Findings: The parallel analysis (PA) recommended one factor as a solution. The initial exploratory factor analysis with a four-factor solution showed low concordance with a four-factor model. Cronbach’s alpha varied from 0.75 to 0.82; however, since two factors only consisted of one item, alpha could not be reported. Cronbach’s alpha for the entire scale showed good homogeneity (α = 0.86). A confirmatory factory analysis was carried out based on the four requirements and showed a goodness-of-fit after deleting two items. After deletion of these items, Cronbach’s alpha was 0.82. Discussion: Based on the exploratory factor analysis, we suggest that the scale should be treated as a one-factor model. The result indicates that the instrument is unidimensional and assesses ethical climate as a whole. Conclusion: After testing the Swedish Ethical Climate Questionnaire, we found support for the validity and reliability of the instrument. We found the 10-item version of Swedish Ethical Climate Questionnaire satisfactory. However, we found no support for measuring different dimensions and, therefore, this instrument should be seen as assessing ethical climate as of whole.

Influences on Catered Event Ordering in a University Workplace: Development and Validation of the Understanding Food Ordering Survey

2018 ◽  
Vol 33 (4) ◽  
pp. 616-619
Author(s):  
Lindsey Menge ◽  
Yueqin Hu ◽  
Sylvia Hurd Crixell ◽  
Lisa Lloyd ◽  
Janet Bezner ◽  
...  
Keyword(s):  
Focus Groups ◽  
Factor Model ◽  
Principal Component ◽  
Equation Modeling ◽  
Paired Samples ◽  
Administrative Assistants ◽  
Central Texas ◽  
Workplace Development ◽  
Test Retest Reliability ◽  
Fit Index

Purpose: To develop and validate an instrument to identify factors that influence what is ordered for catered events for employees at a large university. Design: Themes derived from focus groups were used to develop a survey. Setting: A large public university in central Texas. Subjects: Twenty-seven administrative assistants who order food participated in focus groups, 138 completed the survey, and 31 completed the survey a second time. Measures: One hundred fourteen-question, 5-point Likert scale survey. Analysis: Principal component analyses explored constructs. Confirmatory factor analysis confirmed structure validity. Test -retest analyses assessed reliability. Results: The final survey, the Understanding Food Ordering Survey (UFO), included 19 items within 3 factors; all factor loadings were above 0.3, with no cross-loadings. Three factors explained 55.5% of the variance. Cronbach α values of .846 for social influences from supervisors/coworkers, .838 for restrictions on ordering due to policies/vendors/attendee feedback, .893 for personal views about nutrition, and .831 for the total affirmed reliability. Test–retest reliability was acceptable ( r = 0.780), and paired samples t test indicated no differences between assessments, mean difference = −0.062, standard deviation = 0.29, t (30) = −1.18, P = .247. Structure equation modeling indicated a good fit between the proposed 3-factor model and observed data, with comparative fit index = 0.921 and root means square error of approximation = 0.074. Conclusion: Interventions to improve the nutritional quality of foods selected for catering may benefit from addressing contributory factors while considering a top-down approach to changing the workplace culture.

The Self-Transcendence Scale

2011 ◽  
Vol 30 (3) ◽  
pp. 147-159 ◽  
Author(s):  
Gørill Haugan ◽  
Toril Rannestad ◽  
Helge Garåsen ◽  
Randi Hammervold ◽  
Geir Arild Espnes
Keyword(s):  
Factor Analysis ◽  
Confirmatory Factor Analysis ◽  
Goodness Of Fit ◽  
Factor Model ◽  
Well Being ◽  
The Self ◽  
Mean Square ◽  
Confirmatory Factor ◽  
Self Transcendence ◽  
Fit Index

Purpose: Self-transcendence, the ability to expand personal boundaries in multiple ways, has been found to provide well-being. The purpose of this study was to examine the dimensionality of the Norwegian version of the Self-Transcendence Scale, which comprises 15 items. Background: Reed’s empirical nursing theory of self-transcendence provided the theoretical framework; self-transcendence includes an interpersonal, intrapersonal, transpersonal, and temporal dimension. Design: Cross-sectional data were obtained from a sample of 202 cognitively intact elderly patients in 44 Norwegian nursing homes. Results: Exploratory factor analysis revealed two and four internally consistent dimensions of self-transcendence, explaining 35.3% (two factors) and 50.7% (four factors) of the variance, respectively. Confirmatory factor analysis indicated that the hypothesized two- and four-factor models fitted better than the one-factor model (c x2, root mean square error of approximation, standardized root mean square residual, normed fit index, nonnormed fit index, comparative fit index, goodness-of-fit index, and adjusted goodness-of-fit index). Conclusions: The findings indicate self-transcendence as a multifactorial construct; at present, we conclude that the two-factor model might be the most accurate and reasonable measure of self-transcendence. Implications: This research generates insights in the application of the widely used Self-Transcendence Scale by investigating its psychometric properties by applying a confirmatory factor analysis. It also generates new research-questions on the associations between self-transcendence and well-being.

Model Persamaan Struktur untuk Mengkaji Penggunaan Kenderaan tidak Bermotor Berdasarkan Teori Tingkah Laku Terancang

2013 ◽  
Vol 62 (1) ◽  
Author(s):  
Muhamad Razuhanafi Mat Yazid
Keyword(s):  
Confirmatory Factor ◽  
Fit Index ◽  
Tucker Lewis Index

Konsep pengangkutan tidak bermotor adalah penting bagi menjamin kehidupan dalam persekitaran yang bersih, sihat dan berkualiti tinggi. Hari ini, sistem pengangkutan bandar-bandar di Malaysia mempunyai imej buruk seperti kesesakan, kemalangan, ketiadaan pengangkutan awam sebagai alternatif serta konflik pembebasan gas karbon ke ruang atmosfera menyumbang kepada pencemaran alam dan kepincangan dari aspek kualiti mobiliti kehidupan secara umumnya. Tujuan kajian ini adalah untuk mengukur kesahan dan kebolehpercayaan Instrumen model kenderaan tidak bermotor. Instrumen 4 konstruk yang mengandungi 17 item skala 5 mata telah digunakan dalam kajian ini. Instrumen ini telah ditadbirkan kepada 400 orang responden di bandar Kota Bharu yang dipilih secara rawak berkelompok. Perisian Amos versi 7 digunakan untuk menganalisis data. Nilai Comparative Fit Index (CFI), Tucker Lewis Index (TLI) dan RMSEA digunakan untuk mengekal dan menggugurkan item. Dapatan akhir kajian menggunakan model pengukuran confirmatory factor analisis telah menggugurkan 7 item dan mengekalkan 10 item yang sah dan boleh dipercayai untuk mengukur 4 konstruk. Instrumen ini boleh digunakan untuk membentuk model penggunaan kenderaan tidak bermotor berdasarkan teori tingkah laku terancang (TPB) iaitu berbasikal dan berjalan kaki dalam menjadikannya sebagai mod pengangkutan pilihan di Malaysia.

Sign in / Sign up

Export Citation Format

Share Document