Sonya K. Sterba 《Multivariate behavioral research》2019,54(2):264-287

In structural equation modeling applications, parcels—averages or sums of subsets of item scores—are often used as indicators of latent constructs. Parcel-allocation variability (PAV) is variability in results that arises within sample across alternative item-to-parcel allocations. PAV can manifest in all results of a parcel-level model (e.g., model fit, parameter estimates, standard errors, and inferential decisions). It is a source of uncertainty in parcel-level model results that can be investigated, reported, and accounted for. Failing to do so raises representativeness and replicability concerns. However, in recent methodological literature (Cole, Perkins, &; Zelkowitz, 2016 Cole, D. A., Perkins, C. E., &; Zelkowitz, R. L. (2016). Impact of homogeneous and heterogeneous parceling strategies when latent variables represent multidimensional constructs. Psychological Methods, 21(2), 164–174. doi: 10.1037/met0000047[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]; Little, Rhemtulla, Gibson, &; Shoemann, 2013 Little, T. D., Rhemtulla, M., Gibson, K., &; Schoemann, A. M. (2013). Why the items versus parcels controversy needn't be one. Psychological Methods, 18(3), 285–300. doi: 10.1037/a0033266[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]; Marsh, Ludtke, Nagengast, Morin, &; von Davier, 2013 Marsh, H. W., Lüdtke, O., Nagengast, B., Morin, A., &; von Davier, M. (2013). Why item parcels are (almost) never appropriate: Two wrongs do not make a right—camouflaging misspecification with item parcels in CFA models. Psychological Methods, 18(3), 257–284. doi: 10.1037/a0032773[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]; Rhemtulla, 2016 Rhemtulla, M. (2016). Population performance of SEM parceling strategies under measurement and structural model misspecification. Psychological Methods, 21(3), 348–368. doi: 10.1037/met0000072[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]) parceling has been justified and recommended in several situations without quantifying or accounting for PAV. In this article, we explain and demonstrate problems with these rationales. Overall, we find that: (1) using a purposive parceling algorithm for a multidimensional construct does not avoid PAV; (2) passing a test of unidimensionality of the item-level model need not avoid PAV; and (3) a desire to improve power for detecting structural misspecification does not warrant parceling without addressing PAV; we show how to simultaneously avoid PAV and obtain even higher power by comparing item-level models differing in structural constraints. Implications for practice are discussed.  相似文献   

    

Zachary F. Fisher  Kenneth A. Bollen  Kathleen M. Gates 《Multivariate behavioral research》2019,54(2):246-263

Structural equation modeling (SEM) is an increasingly popular method for examining multivariate time series data. As in cross-sectional data analysis, structural misspecification of time series models is inevitable, and further complicated by the fact that errors occur in both the time series and measurement components of the model. In this article, we introduce a new limited information estimator and local fit diagnostic for dynamic factor models within the SEM framework. We demonstrate the implementation of this estimator and examine its performance under both correct and incorrect model specifications via a small simulation study. The estimates from this estimator are compared to those from the most common system-wide estimators and are found to be more robust to the structural misspecifications considered.  相似文献   

    

Urbano Lorenzo-Seva  Pere J. Ferrando 《Multivariate behavioral research》2019,54(1):15-30

This article proposes a procedure for fitting a pure exploratory bifactor solution in which the general factor is orthogonal to the group factors, but the loadings on the group factors can satisfy any orthogonal or oblique rotation criterion. The proposal combines orthogonal Procrustes rotations with analytical rotations and consists of a sequence of four steps. The basic input is a semispecified target matrix that can be (a) defined by the user, (b) obtained by using Schmid-Leiman orthogonalization, or (c) automatically built from a conventional unrestricted solution based on a prescribed number of factors. The relevance of the proposal and its advantages over existing procedures is discussed and assessed via simulation. Its feasibility in practice is illustrated with two empirical examples in the personality domain.  相似文献   

    

《PsyCh Journal》2018,7(1):25-30

This study examined the factor structure of the Chinese version of the Dysexecutive Questionnaire (DEX) in a large nonclinical sample of college students (n = 1,586). All participants completed the self‐report version of the DEX. An exploratory factor analysis was first performed on a sub‐sample (randomly split, n = 766) and produced a four‐factor model (Volition, Intentionality, Inhibition, and Abstract Problem‐Solving), which was similar to previous models reported in Western samples. In addition, a series of confirmatory factor analyses was conducted on the remaining sample (n = 820). The findings suggested that a four‐factor solution of the self‐report DEX might better explain the latent structure in the present healthy Chinese sample.  相似文献   

    

Francisco J. Abad  Eduardo Garcia-Garzon  Luis E. Garrido  Juan R. Barrada 《Multivariate behavioral research》2017,52(4):416-429

The current study proposes a new bi-factor rotation method, Schmid-Leiman with iterative target rotation (SLi), based on the iteration of partially specified target matrices and an initial target constructed from a Schmid-Leiman (SL) orthogonalization. SLi was expected to ameliorate some of the limitations of the previously presented SL bi-factor rotations, SL and SL with target rotation (SLt), when the factor structure either includes cross-loadings, near-zero loadings, or both. A Monte Carlo simulation was carried out to test the performance of SLi, SL, SLt, and the two analytic bi-factor rotations, bi-quartimin and bi-geomin. The results revealed that SLi accurately recovered the bi-factor structures across the majority of the conditions, and generally outperformed the other rotation methods. SLi provided the biggest improvements over SL and SLt when the bi-factor structures contained cross-loadings and pure indicators of the general factor. Additionally, SLi was superior to bi-quartimin and bi-geomin, which performed inconsistently across the types of factor structures evaluated. No method produced a good recovery of the bi-factor structures when small samples (N = 200) were combined with low factor loadings (0.30–0.50) in the specific factors. Thus, it is recommended that larger samples of at least 500 observations be obtained.  相似文献   

    

Clemens Stachl  Sven Hilbert  Jiew‐Quay Au  Daniel Buschek  Alexander De Luca  Bernd Bischl  Heinrich Hussmann  Markus Bühner 《欧洲人格杂志》2017,31(6):701-722

The present study investigates to what degree individual differences can predict frequency and duration of actual behaviour, manifested in mobile application (app) usage on smartphones. In particular, this work focuses on the identification of stable associations between personality on the factor and facet level, fluid intelligence, demography and app usage in 16 distinct categories. A total of 137 subjects (87 women and 50 men), with an average age of 24 (SD = 4.72), participated in a 90‐min psychometric lab session as well as in a subsequent 60‐day data logging study in the field. Our data suggest that personality traits predict mobile application usage in several specific categories such as communication, photography, gaming, transportation and entertainment. Extraversion, conscientiousness and agreeableness are better predictors of mobile application usage than basic demographic variables in several distinct categories. Furthermore, predictive performance is slightly higher for single factor—in comparison with facet‐level personality scores. Fluid intelligence and demographics additionally show stable associations with categorical app usage. In sum, this study demonstrates how individual differences can be effectively related to actual behaviour and how this can assist in understanding the behavioural underpinnings of personality. Copyright © 2017 European Association of Personality Psychology  相似文献   

    

Tom Rosenström  Markus Jokela 《欧洲人格杂志》2017,31(6):658-668

  相似文献   

    

《Revue Européene de Psychologie Appliquée》2017,67(6):299-306

IntroductionThe Autism Spectrum Questionnaire (AQ, Baron-Cohen et al., 2001) is a self-report assessment tool aiming at screening autistic traits in normal intelligence adults. While numerous versions in other languages than English now exist, few factorial evidence do sustain the valid use of this instrument as it was conceived, based upon five distinct dimensions (Social skills, Communication, Attention to detail, Attention switching, Imagination); no such study exists with a French version of the AQ. The aim of our study is therefore to present the French version of the scale and to explore its factorial validity with confirmatory factorial analyses and, possibly, its invariance across men and women.MethodSeveral confirmatory factorial analyses, with the robust WLSMV estimator for categorical response format, were run on the questionnaire data from 788 French-speaking students (17–25 years old) at university faculties or schools for higher education in Belgium. The original five-factor measurement model of the AQ was assessed as well as alternative models. An exploratory factorial analysis was also applied to get more insight as to possible sources of misfit.ResultsNo measurement model – neither the original five-factor one nor any of the six other models tested – did produce statistics or fit indices close to significant values: there was no fit to the data. The internal consistency of the subscales was weak; the exploratory factorial analysis further confirmed that as much as ten factors were needed to explain 45% of the data variance.ConclusionOur results, with a French version of the scale, add to many other ones which suggest that the AQ is a too heterogeneous questionnaire with somewhat ill-defined dimensions and non specific/ambiguous items. The questionnaire should probably be shortened and its content realigned to core features of the autism spectrum.  相似文献   

    

《Transportation Research Part F: Traffic Psychology and Behaviour》2017

The overrepresentation of young drivers in road crashes, and the fatalities and injuries arising from those crashes, is an intractable problem around the world. A plethora of research has led to the development and application of a range of research tools, including self-report survey instruments. One such instrument, the five-factor Behaviour of Young Novice Driver Scale (BYNDS), was developed in an Australian young driver population, and has recently been validated in a New Zealand young driver population. The current study aimed to validate the BYNDS in a Colombian young driver population, the first application of the instrument in a developing country. Translation from English to Spanish, and back translation from Spanish to English, in addition to culturally-appropriate modifications (such as changing ‘right hand side’ to ‘left hand side’) resulted in a Spanish version of the BYNDS (BYNDS-Sp). The BYNDS-Sp was administered to a sample of 392 young drivers aged 16–24 years (n = 353 aged 19–24 years) with a valid driver’s licence. An exploratory factor analysis revealed a six factor structure using 40 of the original 44 BYNDS-Sp items, accounting for 58.5% of the variance in self-reported risky driving behaviour. Ninety-three percent of participants reported having ready access to their own vehicle (42% owned their own vehicle), with Colombian young drivers most likely to report driving at night and on the weekend. The majority of participants reported driving in excess of posted speed limits (e.g., only one third of participants reported never driving 10–20 km/h over the speed limit), and driving in response to their mood (e.g., only one third of participants reported they never drove faster if in a bad mood). As such, the BYNDS-Sp can reveal patterns of problematic behaviours (such as risky driving exposure), in addition to specific behaviours of concern (such as carrying passengers at night, and driving when tired), guiding the development and implementation of interventions targeting the risky driving behaviour of young drivers in Colombia. In addition, the BYNDS-Sp can be used as a measure of intervention success if used as a baseline and as a follow-up tool. Further research can investigate the utility and applicability of the BYNDS-Sp in other Spanish-speaking countries, such as Spain and Mexico.  相似文献   

    

Naomi Tutticci  Fiona Coyer  Peter A. Lewis  Mary Ryan 《Reflective Practice》2017,18(2):219-231

Background: nursing students are required to think reflectively in both real and simulated clinical practice. Although the Reflective Thinking instrument is reliable in its measurement of reflective thinking, its validity is unknown. Method: confirmatory factor analysis was undertaken in an iterative manner within a non-equivalent control-group study to measure nursing students’ reflective thinking and satisfaction with high-fidelity simulation. The validity and reliability of the Reflective Thinking instrument was tested. Results: the resulting instrument consisted of 15 items across four factors. The final model was plausible as it demonstrated ‘goodness of fit’; however, it had neither convergent or discriminatory validity, nor reliability. Internal consistency was fair to reasonable for the four subscales. Conclusion: the testing of the Reflective Thinking instrument using confirmatory factor analysis is a vital initial step in the modification of this instrument. Further development using exploratory factor analysis will enhance the instrument’s relevance within high-fidelity simulation.  相似文献