How Do Children with Autism Spectrum Disorder and Children with Developmental Delays Differ on the Child Behavior Checklist 1.5–5 DSM-Oriented Scales?

The Child Behavior Checklist 1.5–5 (CBCL 1.5–5) is applied to identify emotional and behavioral problems on children with developmental disabilities (e.g., autism spectrum disorder [ASD] and developmental delays [DD]). To understand whether there are variations between these two groups on CBCL DSM-oriented scales, we took two invariance analyses on 443 children (228 children with ASD). The first analysis used measurement invariance and multiple-group factor analysis on the test structure. The second analysis used item-level analysis, i.e., differential item functioning (DIF), to discover whether group memberships responded differently on some items even though underlying trait levels were the same. It was discovered that, on the test structure, the Anxiety Problems scale did not achieve metric invariance. The other scales achieved metric invariance; DIF analyses further revealed that there were items that functioned differently across subscales. These DIF items were mostly about children’s reactions to the surrounding environment. Our findings provide implications for clinicians to use CBCL DSM-oriented scales on differentiating children with ASD and children with DD. In addition, researchers need to be mindful about how items were responded differently, even though there were no mean differences on the surface.

Measurement invariance of the modified brand luxury index scale across gender, age and countries

PurposeMany instruments have been developed to measure the perceived luxuriousness of brands, but one of the most frequently used scales is the “brand luxury index” (BLI) from Vigneron and Johnson (2004) that distinguishes between high- and low-luxury brands. Despite its popularity and widespread use in academic research, the scale's psychometric properties and equivalence across cultures have been questioned. Recently, modified versions of the scale have been developed to strengthen the quality of the measurement. However, the performance and the measurement invariance of the modified version have not yet been investigated. The current paper aims to test the model fit of the modified BLI scale and the measurement invariance across gender, age and country groups using nine datasets from a total of three different countries.Design/methodology/approachThis paper conducts a multi-group CFA to examine the measurement invariance of the BLI scale. Nine datasets were used in this study. The data were collected across three countries, the United States (5 datasets), China (2 datasets) and India (2 datasets) from 2016 to 2018.FindingsThe results of this analysis suggest that the modified BLI scale has an acceptable model fit and can be interpreted equivalently across gender and age groups. Metric invariance was found among the US, China and India. However, scalar measurement invariance was established only across two countries: the US and India. A follow-up analysis shows that partial scalar invariance can be established across the US, China and India when removing constraints on the parameters of three items: exclusive, precious and sophisticated.Originality/valueThis study is the first study to test the model fit of the modified BLI scale. The findings of this paper contribute to both the academia and industry. The authors recommend scholars and marketers to use a modified 19-item BLI scale to measure the perceived luxuriousness of brands in future research. First, the modified BLI scale tested in the current study offers very good performance with model fit values of a quality that has rarely been seen in prior research. The original scale of Vigneron and Johnson (2004) has been criticized for its poor model fit (Christodoulides et al., 2009). The modified scale of Doss and Robinson (2013) also has problems with the fit value. Second, the modified 19-item scale also shows adequate measurement invariance across different gender, age and countries. For scholars and marketers, the establishment of the metric invariance of the modified 19-item BLI scale implies that the scale can be used across gender, age and countries (the US, China and India) if the purpose of the study is to understand the relationship between some variables and perceived luxuriousness of a brand.

Measurement Invariance of Perfectionism Measures in Students with and without a History of Non-Suicidal Self-Injury

Perfectionism is a transdiagnostic process which may be implicated in the onset and maintenance of non-suicidal self-injury. No study has evaluated whether reported differences in perfectionism between individuals with and without a history of self-injury represent genuine group differences or measurement artefacts. The present study reports an investigation of the measurement invariance of two common scales of perfectionism, the Frost Multidimensional Perfectionism Scale-Brief (FMPS-Brief) and the Clinical Perfectionism Questionnaire (CPQ), among university students (Mage = 20.48, SDage = 2.22, 75.3% female, 22.8% male) with and without a history of self-injury (total n = 711). Results revealed full residual error invariance for the two-factor model of FMPS-Brief, while the bifactor model of the FMPS-Brief and the two-factor model of the CPQ demonstrated partial metric invariance. Accounting for partial metric invariance, the bifactor model of the FMPS-Brief also demonstrated partial residual error invariance. The current findings suggest that observed differences using the FMPS-Brief reflect genuine differences in perfectionism between individuals with and without a history of self-injury. Further, while researchers using the bi-factor model can have confidence that the general factor can adequately assess group differences, differential item functioning should be considered if using the strivings and concerns factors. Finally, in the current data, the CPQ did not perform as expected in baseline model fit and future research should replicate assessments of measurement invariance in this measure.

Factorial Structure of the Transactional eHealth Literacy Among Vietnamese Youth: An Instrument Validation Study

The progression into the Digital Age has brought an array of novel skill requirements. Unlike traditional literacy, there are currently few measures that can reliably measure eHealth literacy. The Transactional Model of eHealth Literacy and subsequent Transactional eHealth Literacy Instrument may provide a feasible option for measuring eHealth literacy. However, this instrument has yet to be validated, which is the aim of this study. We conducted an online cross-sectional study among 236 Vietnamese young people. Using exploratory factor analysis, we ensured that a model consisting of four factors had the best fit (RMSEA = 0.116; CFI = 0.907) and the highest internal consistency (Cronbach alpha = 0.96). A confirmatory factor analysis tested measurement invariance at four levels: configural, metric, scalar, and strict invariance. Only metric invariance was partially invariant, while the rest tested fully invariant. Even with partial metric invariance, there is reason to assume that functional, communicative, critical, and translational eHealth literacy (the four levels according to the transactional model) are consistently measured when deploying the Transactional eHealth Literacy Instrument across groups. In other words, this study suggests the instrument can be used for comparisons across groups and has the potential to generate high-quality data usable for informing change agents as to whether a particular population is proficient enough to adopt novel eHealth innovations.

Measurement Invariance of Three Brief Measures of Rumination in Young Adults With and Without a History of Self-Injury

Rumination is central to understanding the onset and maintenance of non-suicidal self-injury. Yet, no study has evaluated whether reported differences in rumination between people with and without a history of self-injury represent genuine group differences. The present study reports an investigation into the measurement invariance of three common measures of rumination in university students with and without a history of self-injury (total N = 1,519). Results revealed configural invariance for the Ruminative Responses Scale (RRS), the Ruminative Thought Style Questionnaire (RTSQ), and the Repetitive Thinking Questionnaire (RTQ). Additionally, the RTSQ and RTQ supported metric invariance, while the RRS supported partial metric invariance. Further, the RTQ demonstrated partial scalar invariance while the RTSQ demonstrated full scalar invariance. The current findings suggest that observed differences using the RTSQ and RTQ reflect genuine differences in rumination between people with and without a history of self-injury, while researchers using the RRS are advised to account for differential item functioning.

Finding clusters of groups with measurement invariance: Unraveling intercept non-invariance with mixture multigroup factor analysis

Comparisons of latent constructs across groups are ubiquitous in behavioral research and, nowadays, often numerous groups are involved. Measurement invariance of the constructs across the groups is imperative for valid comparisons and can be tested by multigroup factor analysis. For many groups, metric invariance (invariant factor loadings) often holds, whereas scalar invariance (invariant intercepts) is rarely supported. Scalar invariance is a prerequisite for comparing latent means, however. One may inspect group-specific intercepts to pinpoint non-invariances, but this is a daunting task in case of many groups. This paper presents mixture multigroup factor analysis (MMG-FA) for clustering groups based on their intercepts. Clusters of groups with scalar invariance are obtained by imposing cluster-specific intercepts and invariant loadings whereas unique variances, factor means and factor (co)variances can differ between groups. Thus, MMG-FA ties down the number of intercepts to inspect and generates clusters of groups wherein latent means can be validly compared.

Finding clusters of groups with measurement invariance: Unraveling intercept non-invariance with mixture multigroup factor analysis

Comparisons of latent constructs across groups are ubiquitous in behavioral research and, nowadays, often numerous groups are involved. Measurement invariance of the constructs across the groups is imperative for valid comparisons and can be tested by multigroup factor analysis. For many groups, metric invariance (invariant factor loadings) often holds, whereas scalar invariance (invariant intercepts) is rarely supported. Scalar invariance is a prerequisite for comparing latent means, however. One may inspect group-specific intercepts to pinpoint non-invariances, but this is a daunting task in case of many groups. This paper presents mixture multigroup factor analysis (MMG-FA) for clustering groups based on their intercepts. Clusters of groups with scalar invariance are obtained by imposing cluster-specific intercepts and invariant loadings whereas unique variances, factor means and factor (co)variances can differ between groups. Thus, MMG-FA ties down the number of intercepts to inspect and generates clusters of groups wherein latent means can be validly compared.

Assessing the Importance of Internal and External Self-Esteem and Their Relationship to Honor Concerns in Six Countries

We assessed empirical support for (a) the widely held notion that across so-called “honor, dignity, and face cultures,” internal and external components of self-esteem are differentially important for overall self-esteem; and (b) the idea that concerns for honor are related to internal and external components of self-esteem in honor cultures but not in dignity and face cultures. Most importantly, we also set out to (c) investigate whether measures are equivalent, that is, whether a comparison of means and relationships across cultural groups is possible with the employed scales. Data were collected in six countries ( N = 1,099). We obtained only metric invariance for the self-esteem and honor scales, allowing for comparisons of relationships across samples, but not scale means. Partly confirming theoretical ideas on the importance of internal and external components of self-esteem, we found that only external rather than both external and internal self-esteem was relatively more important for overall self-esteem in “honor cultures”; in a “dignity” culture, internal self-esteem was relatively more important than external self-esteem. Contrary to expectations, in a “face” culture, internal self-esteem was relatively more important than external self-esteem. We were not able to conceptually replicate earlier reported relationships between components of self-esteem and the concern for honor, as we observed no cultural differences in the relationship between self-esteem and honor. We point toward the need for future studies to consider invariance testing in the field of honor to appropriately understand differences and similarities between samples.

The Uniform Dataset 3.0 Neuropsychological Battery: Factor Structure, Invariance Testing, and Demographically Adjusted Factor Score Calculation

Objective:The goals of this study were to (1) specify the factor structure of the Uniform Dataset 3.0 neuropsychological battery (UDS3NB) in cognitively unimpaired older adults, (2) establish measurement invariance for this model, and (3) create a normative calculator for factor scores.Methods:Data from 2520 cognitively intact older adults were submitted to confirmatory factor analyses and invariance testing across sex, age, and education. Additionally, a subsample of this dataset was used to examine invariance over time using 1-year follow-up data (n = 1061). With the establishment of metric invariance of the UDS3NB measures, factor scores could be extracted uniformly for the entire normative sample. Finally, a calculator was created for deriving demographically adjusted factor scores.Results:A higher order model of cognition yielded the best fit to the data χ2(47) = 385.18, p < .001, comparative fit index = .962, Tucker-Lewis Index = .947, root mean square error of approximation = .054, and standardized root mean residual = .036. This model included a higher order general cognitive abilities factor, as well as lower order processing speed/executive, visual, attention, language, and memory factors. Age, sex, and education were significantly associated with factor score performance, evidencing a need for demographic correction when interpreting factor scores. A user-friendly Excel calculator was created to accomplish this goal and is available in the online supplementary materials.Conclusions:The UDS3NB is best characterized by a higher order factor structure. Factor scores demonstrate at least metric invariance across time and demographic groups. Methods for calculating these factors scores are provided.