scholarly journals Three recommendations based on a comparison of the reliability and validity of the predominant models used in research on the empirical structure of psychopathology

2020 ◽  
Author(s):  
Miriam K. Forbes ◽  
Ashley Lauren Greene ◽  
Holly Levin-Aspenson ◽  
Ashley L. Watts ◽  
Michael Hallquist ◽  
...  
Keyword(s):  
Factor Model ◽  
Reliability And Validity ◽  
The United States ◽  
Higher Order ◽  
Bifactor Model ◽  
Model Fit ◽  
General Factor ◽  
Single Factor ◽  
Over Time ◽  
Single Factor Model

The present study compared the primary models used in research on the structure of psychopathology (i.e., correlated factor, higher-order, and bifactor models) in terms of structural validity (model fit and factor reliability), longitudinal measurement invariance, concurrent and prospective predictive validity in relation to important outcomes, and longitudinal consistency in individuals’ factor score profiles. Two simpler operationalizations of a general factor of psychopathology were also examined—a single-factor model and a count of diagnoses. Models were estimated based on structured clinical interview diagnoses in two longitudinal waves of nationally representative data from the United States (n = 43,093 and n = 34,653). Models that included narrower factors (fear, distress, and externalizing) were needed to capture the observed multidimensionality of the data. In the correlated factor and higher-order models these narrower factors were reliable, largely invariant over time, had consistent associations with indicators of adaptive functioning, and had moderate stability within individuals over time. By contrast, the fear and distress specific factors in the bifactor model did not show good reliability or validity throughout the analyses. Notably, the general factor of psychopathology (p-factor) performed similarly well across tests of reliability and validity regardless of whether the higher-order or bifactor model was used; the simplest (single-factor) model was also comparable across most tests, with the exception of model fit. Given the limitations of categorical diagnoses, it will be important to repeat these analyses using dimensional measures. We conclude that when aiming to understand the structure and correlates of psychopathology it is important to: 1) look beyond model fit indices to choose between different models; 2) examine the reliability of latent variables directly; and 3) be cautious when isolating and interpreting the unique effects of specific psychopathology factors, regardless of which model is used.

Higher-Order and Bifactor Models of the Drinking Motives Questionnaire

Assessment ◽  
2016 ◽  
Vol 24 (2) ◽  
pp. 222-231 ◽  
Author(s):  
Andrew Lac ◽  
Candice D. Donaldson
Keyword(s):  
Structural Equation ◽  
Negative Reinforcement ◽  
Factor Model ◽  
Equation Model ◽  
Higher Order ◽  
Bifactor Model ◽  
Drinking Motives ◽  
General Factor ◽  
Fit Indices ◽  
Confirmatory Factor Analyses

The Drinking Motives Questionnaire, previously postulated and documented to exhibit a measurement structure of four correlated factors (social, enhancement, conformity, and coping), is a widely administered assessment of reasons for consuming alcohol. In the current study ( N = 552), confirmatory factor analyses tested the plausibility of several theoretically relevant factor structures. Fit indices corroborated the original four-factor model, and also supported a higher-order factor model involving a superordinate motives factor that explicated four subordinate factors. A bifactor model that permitted items to double load on valence type (positive or negative reinforcement) and source type (external or internal) generated mixed results, suggesting that this 2 × 2 motivation paradigm was not entirely tenable. Optimal fit was obtained for a bifactor model depicting a general factor and four specific factors of motives. Latent factors derived from this structure exhibited criterion validity in predicting frequency and quantity of alcohol usage in a structural equation model. Findings are interpreted in the context of theoretical implications of the instrument, alternative factor structures of drinking motives, and assessment applications.

Measuring Positive Mental Health in the Postpartum Period: The Bifactor Structure of the Mental Health Continuum–Short Form in Portuguese Women

Assessment ◽  
2020 ◽  
pp. 107319112091024 ◽  
Author(s):  
Fabiana Monteiro ◽  
Ana Fonseca ◽  
Marco Pereira ◽  
Maria Cristina Canavarro
Keyword(s):  
Mental Health ◽  
Factor Model ◽  
Short Form ◽  
High Reliability ◽  
Reliability And Validity ◽  
Total Sample ◽  
Bifactor Model ◽  
Positive Mental Health ◽  
General Factor ◽  
Explained Common Variance

This study aimed to investigate the factor structure of the Mental Health Continuum–Short Form (MHC-SF) in the postpartum context using a single-factor model, a correlated three-factor model, and a bifactor model. The reliability and validity of the MHC-SF were also examined. The total sample consisted of 882 postpartum Portuguese women. Confirmatory factor analysis showed that the bifactor model yielded a significantly better fit to the data than the other models. The unidimensionality strength indices (explained common variance = .76, percentage of uncontaminated correlations = .69) and the ω H values supported the general factor of positive mental health, which accounted for 91.5% of the reliable variance in the total score. Additionally, the MHC-SF showed high reliability (ω = .96), and its total and subscale scores were significantly correlated with other measures related to mental health. The results of this study suggest a strong general factor of positive mental health and support the use of its total score in this context.

scholarly journals Comparing Job Applicants to Non–Applicants Using An Item–Level Bifactor Model on the Hexaco Personality Inventory

2017 ◽  
Vol 31 (6) ◽  
pp. 669-684 ◽  
Author(s):  
Jeromy Anglim ◽  
Gavin Morse ◽  
Reinout E. De Vries ◽  
Carolyn MacCann ◽  
Andrew Marty ◽  
...  
Keyword(s):  
Social Desirability ◽  
Factor Model ◽  
Higher Order ◽  
Personality Inventory ◽  
Bifactor Model ◽  
General Factor ◽  
Personality Psychology ◽  
Job Applicant ◽  
Item Level ◽  
Improved Model

The present study evaluated the ability of item–level bifactor models (a) to provide an alternative explanation to current theories of higher order factors of personality and (b) to explain socially desirable responding in both job applicant and non–applicant contexts. Participants (46% male; mean age = 42 years, SD = 11) completed the 200–item HEXACO Personality Inventory–Revised either as part of a job application ( n = 1613) or as part of low–stakes research ( n = 1613). A comprehensive set of invariance tests were performed. Applicants scored higher than non–applicants on honesty–humility ( d = 0.86), extraversion ( d = 0.73), agreeableness ( d = 1.06), and conscientiousness ( d = 0.77). The bifactor model provided improved model fit relative to a standard correlated factor model, and loadings on the evaluative factor of the bifactor model were highly correlated with other indicators of item social desirability. The bifactor model explained approximately two–thirds of the differences between applicants and non–applicants. Results suggest that rather than being a higher order construct, the general factor of personality may be caused by an item–level evaluative process. Results highlight the importance of modelling data at the item–level. Implications for conceptualizing social desirability, higher order structures in personality, test development, and job applicant faking are discussed. Copyright © 2017 European Association of Personality Psychology

scholarly journals “Test Your Spirituality in One Minute or Less” Structural Validity of the Multidimensional Inventory for Religious/Spiritual Well-Being Short Version (MI-RSWB 12)

2021 ◽  
Vol 12 ◽  
Author(s):  
Jürgen Fuchshuber ◽  
Human F. Unterrainer
Keyword(s):  
Lower Order ◽  
Factor Model ◽  
Well Being ◽  
Higher Order ◽  
Bifactor Model ◽  
Short Version ◽  
Single Factor ◽  
Order Model ◽  
Structural Validity ◽  
Spiritual Well Being

Background: The Multidimensional Inventory for Religious/Spiritual Well-Being (MI-RSWB 48) was developed in order to address a religious/spiritual dimension as being an important part of psychological well-being. In the meantime, the instrument has been successfully applied in numerous studies. Subsequently, a short version, the MI-RSWB 12 was constructed, especially for the use in clinical assessment. Here it is intended to contribute to the further development of the MI-RSWB 12 by investigating its structural validity through structural equation modeling.Materials and Methods: A total sample of 1,097 German-speaking adults (744 females; 67.8%; Age range: 18–69 years) from the normal population filled in the MI-RSWB 12 via an online-survey. In line with theoretical assumptions 5 different factor structure models for the MI-RSWB 12 were tested: (1) a single-factor model, (2) a model with four correlated RSWB dimensions, (3) a single higher-order model with four lower order factors, (4) a two higher-order model with four lower order factors, (5) a bifactor model, which includes four specific RSWB dimensions.Results: The single-factor model provided the poorest model fit, with no indices falling within the acceptable range. The four-factor, two higher-order factors and the bifactor models showed overall acceptable fit indices. With regard to the Akaike information criterion (AIC), the four-factor model demonstrated superiority compared to both the two higher-order factor model and the bifactor model, which in turn showed did not differ from each other.Conclusion: Four different MI-RSWB 12 sub-scales should be calculated in future studies, while a general factor and two higher order factors are statistically valid as well. Further applications of the MI-RSWB 12, especially in the clinical patient groups, are encouraged.

scholarly journals Comparing Job Applicants to Non-Applicants Using an Item-Level Bifactor Model on the HEXACO Personality Inventory

2017 ◽  
Author(s):  
Jeromy Anglim ◽  
Gavin Morse ◽  
Reinout E. de Vries ◽  
Carolyn MacCann ◽  
Andrew Marty
Keyword(s):  
Social Desirability ◽  
Factor Model ◽  
Higher Order ◽  
Personality Inventory ◽  
Bifactor Model ◽  
Order Structure ◽  
General Factor ◽  
Job Applicant ◽  
Item Level ◽  
Improved Model

The present study evaluated the ability of item-level bifactor models (a) to provide an alternative explanation to current theories of higher-order factors of personality, and (b) to explain socially desirable responding in both job applicant and non-applicant contexts. Participants (46% male; mean age=42 years, SD=11) completed the 200- item HEXACO Personality Inventory-Revised (HEXACO PI-R) either as part of a job application (n = 1613) or as part of low-stakes research (n = 1613). A comprehensive set of invariance test were performed. Applicants scored higher than non-applicants on honesty- humility (d = 0.86), extraversion (d = 0.73), agreeableness (d = 1.06), and conscientiousness (d = 0.77). The bifactor model provided improved model fit relative to a standard correlated factor model, and loadings on the evaluative factor of the bifactor model were highly correlated with other indicators of item social desirability. The bifactor model explained approximately two-thirds of the differences between applicants and non- applicants. Results suggest that rather than being a higher-order construct, the general factor of personality may be caused by an item- level evaluative process. Results highlight the importance of modelling data at the item-level. Implications for conceptualizing social desirability, higher-order structure in personality, test development, and job applicant faking are discussed.

scholarly journals Psychometric Evaluation of the Perceived Stress Scale in Multiple Sclerosis

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Salene M. Wu ◽  
Dagmar Amtmann
Keyword(s):  
Multiple Sclerosis ◽  
Perceived Stress ◽  
Factor Model ◽  
Reliability And Validity ◽  
Psychometric Evaluation ◽  
General Factor ◽  
Perceived Stress Scale ◽  
Stress Scale ◽  
Two Factors ◽  
Mental And Physical Health

Multiple sclerosis (MS) is a progressive disease characterized by neurological symptoms and sometimes heightened levels of distress. The Perceived Stress Scale (PSS) is often used in MS samples to measure stress but has not been validated in this population. Participants (n=446) completed the PSS as well as measure of depression, anxiety, and mental and physical health. Factor analyses indicated that the general factor of a bifactor model accounted for a large amount of the variance in the 14-item and 10-item versions of the PSS. The 4-item PSS had two factors, the Stress subscale and the Coping subscale, but a one-factor model also fits the data well. Total scores and both subscales had sufficient reliability and validity for all versions of the PSS, although a few items of the 14-item PSS had low item-total correlations. This study supports the use of the total score of the PSS in MS but also suggests that the 10-item PSS had better psychometric properties than the 14-item PSS.

The Test of Gross Motor Development—Third Edition: A Bifactor Model, Dimensionality, and Measurement Invariance

2021 ◽  
pp. 1-16
Author(s):  
Sedigheh Salami ◽  
Paulo Felipe Ribeiro Bandeira ◽  
Cristiano Mauro Assis Gomes ◽  
Parvaneh Shamsipour Dehkordi
Keyword(s):  
Measurement Invariance ◽  
Motor Development ◽  
Goodness Of Fit ◽  
Factor Model ◽  
Bifactor Model ◽  
General Factor ◽  
Convenience Sample ◽  
Gross Motor ◽  
Measurement Models ◽  
Gross Motor Development

Aim: To examine the latent structure of the Test of Gross Motor Development—Third Edition (TGMD-3) with a bifactor modeling approach. In addition, the study examines the dimensionality and model-based reliability of general and specific contributions of the test’s subscales and measurement invariance of the TGMD-3. Methods: A convenience sample of (N = 496; Mage = 7.23 ± 2.03 years; 53.8% female) typically developed children participated in this study. Three alternative measurement models were tested: (a) a unidimensional model, (b) a correlated two-factor model, and (c) a bifactor model. Results: The totality of results, including item loadings, goodness-of-fit indexes, and reliability estimates, all supported the bifactor model and strong evidence of a general factor, namely gross motor competence. Additionally, the reliability of subscale scores was poor, and it is thus contended that scoring, reporting, and interpreting of the subscales scores are probably not justifiable. Conclusions: This study shows the advantages of using bifactor approach to examine the TGMD-3 factor structure and suggests that the two traditionally hypothesized factors are better understood as “grouping” factors rather than as representative of latent constructs. In addition, our findings demonstrate that the bifactor model appears invariant for sex.

scholarly journals Cross-Cultural Evaluation of Antonovsky’s Orientation to Life Questionnaire: Comparison Between Australian, Finnish, and Turkish Young Adults

2018 ◽  
Vol 122 (2) ◽  
pp. 731-747 ◽  
Author(s):  
Timo Lajunen
Keyword(s):  
Cultural Differences ◽  
Factor Model ◽  
Well Being ◽  
Cross Cultural ◽  
Life Questionnaire ◽  
Single Factor ◽  
Scale Scores ◽  
Health And Well Being ◽  
Three Factor ◽  
Single Factor Model

Antonovsky’s concept “sense of coherence” (SOC) and the related measurement instrument “The Orientation to Life Questionnaire” (OLQ) has been widely applied in studies on health and well-being. The purpose of the present study is to investigate the cultural differences in factor structures and psychometric properties as well as mean scores of the 13-item form of Antonovsky’s OLQ among Australian (n = 201), Finnish (n = 203), and Turkish (n = 152) students. Three models of factor structure were studied by using confirmatory factor analysis: single-factor model, first-order correlated-three-factor model, and the second-order three-factor model. Results obtained in all three countries suggest that the first- and second-order three-factor models fitted the data better that the single-factor model. Hence, the OLQ scoring based on comprehensibility, manageability, and meaningfulness scales was supported. Scale reliabilities and inter-correlations were in line with those reported in earlier studies. Two-way analyses of variance (gender × nationality) with age as a covariate showed no cultural differences in SOC scale scores. Women got higher scores on the meaningfulness scale than men, and age was positively related to all SOC scale scores indicating that SOC increases in early adulthood. The results support the three-factor model of OLQ which thus should be used in Australia, Finland, and Turkey instead of a single-factor model. Need for cross-cultural studies taking into account cultural correlates of SOC and its relation to health and well-being indicators as well as studies on gender differences in the OLQ are emphasized.

scholarly journals Examining the Impostor-Profile—Is There a General Impostor Characteristic?

2021 ◽  
Vol 12 ◽  
Author(s):  
Fabio Ibrahim ◽  
Johann-Christoph Münscher ◽  
Philipp Yorck Herzberg
Keyword(s):  
Convergent Validity ◽  
Factor Model ◽  
Second Order ◽  
Model Fit ◽  
Impostor Phenomenon ◽  
General Factor ◽  
Order Model ◽  
First Order ◽  
Order Factor ◽  
Best Fit

The Impostor-Profile (IPP) is a six-dimensional questionnaire measuring the Impostor Phenomenon facets. This study aims to test (a) the appropriateness of a total score, (b) measurement invariance (MI) between gender, (c) the reliability of the IPP, and (d) the convergent validity of the IPP subscales. The sample consisted of N = 482 individuals (64% female). To identify whether the scales of the IPP form a total score, we compared four models: (1) six correlating subscales, (2) a general factor model, (3) a second-order model with one second-order factor and six first-order factors, and (4) a bifactorial model with six group factors. The bifactorial model obtained the best fit. This supports the assumption of a total impostor score. The inspection of structural validity between gender subgroups showed configural, metric, and partial scalar MI. Factor mean comparisons supported the assumption that females and males differ in latent means of the Impostor Phenomenon expressions. The omega coefficients showed sufficient reliability (≥0.71), except for the subscale Need for Sympathy. Overall, the findings of the bifactor model fit and construct validity support the assumption that the measurement through total expression is meaningful in addition to the theoretically formulated multidimensionality of the Impostor Phenomenon.

Sign in / Sign up

Export Citation Format

Share Document