Longitudinal Factorial Invariance Research Articles

Examining the longitudinal associations between activity limitations, instrumental supports and social participation in osteoarthritis: A CLSA population-based study.

In osteoarthritis (OA) research, disability is largely studied within the context of activities of daily living. Broader consequences for social participation are often overlooked. In prior work, instrumental supports received and their perceived availability were shown to play a role in the maintenance of social participation. Two indicators of social participation were identified, diversity and intensity. The current study extends the findings from this prior cross-sectional work by examining these relationships longitudinally. Data are from the baseline and 3-year follow-up questionnaires of the Canadian Longitudinal Study on Aging, a population-based study of people ages 45-85 years at baseline. The sample was restricted to those who at baseline reported a doctor diagnosis of OA (n = 4104). Using structural equation modeling, latent variables were derived at each time point for activity limitations, instrumental supports perceived and received, and social participation diversity and intensity. Longitudinal factorial invariance was assessed. Model covariates included age, sex, education, income, marital status, smoking status, obesity, and number of chronic conditions. For all latent variables, strong factorial longitudinal invariance was found. Activity limitations increased over time. Greater baseline social participation intensity was associated with increases in later intensity and diversity. Increasing activity limitations were associated with decreases in social participation and with increasing receipt of instrumental supports; they were not associated with changes in perceived availability of supports. However, increasing perceived availability was positively associated with social participation intensity. With a goal of increasing social participation, findings suggest a focus on interventions to reduce activity limitations in OA is necessary. Findings additionally highlight an important role for perceived availability of instrumental supports in maintaining or improving social participation in OA, in addition to current social participation, particularly intensity, for future social participation status.

Longitudinal Factorial Invariance of a Brief Measure of Affect and Calm Focus.

Mindfulness-based practices for school-aged children are increasingly common in the United States. Positive and negative affect are theoretically and empirically associated with school outcomes, and these constructs are likely to be impacted by school-based mindfulness practices. Furthermore, mindful states, such as being calm and focused, targeted by mindfulness-based practices are a potential causal mechanism to improve learning and behavior. This study describes a test of longitudinal factorial invariance for a brief measure of affect states plus a state of calm focus that is appropriate for use in mindfulness intervention studies with elementary school-aged children. Data were collected from 97 fourth-grade students in an urban elementary school that was about 46% Hispanic and 44% White. Students listened to one of six different conditions each day for 24 school days: There were four individual mindfulness modules (cross-connect, pause buttons, belly breathing, and mindful minute), one condition that included all four of the modules together, and one condition that was a control activity (a grade-appropriate story presented via audiorecording). Students provided self-report of positive and negative emotions plus calm focus immediately before and after the presentation of the audio. Results showed high levels of internal consistency for the scales, low correlations between scales, and factorial invariance in the pre- and post-test design for five of the six conditions. These findings support the use of this measure in studies with older elementary school students. Future studies should further document construct validity through external validation of the scales.

Assessing the Recovery Assessment Scale Across Time.

The Recovery Assessment Scale (RAS) is one of the most used recovery measures in recovery-oriented practice evaluation of people with mental health conditions. Although its psychometric properties have been extensively studied, one critical piece of information that is missing from the literature is evidence of its longitudinal factorial invariance-that is, whether the RAS measures the same recovery construct across time. The authors empirically tested the longitudinal factorial invariance assumption for the RAS. Structural equation modeling was used to test the longitudinal factorial invariance of the RAS with data longitudinally obtained at three time points from 167 people with severe mental illness. The longitudinal factorial invariance assumption was supported (i.e., configural, metric, partial scalar, factor variance and covariance invariance). This study found empirical evidence that the RAS can measure the same recovery construct over time and thus meets one of the important prerequisites for longitudinal assessment.

Fitting Structural Equations Models with Interactive and Dynamic Tools in JMP® Pro

ABSTRACT We offer a tutorial for using a new, interactive, and dynamic Structural Equation Modeling (SEM) platform in JMP Pro v16.0 to fit three commonly used models: (1) Confirmatory Factor Analysis, (2) Path Analysis with Latent Variables, and (3) Longitudinal Factorial Invariance Analysis. We highlight features of JMP Pro through these examples including, an end-to-end workflow that enables all stages of data manipulation, visualization, analysis, and presentation, the dynamic feedback provided in the SEM specification process to guard against errors, interactive customizations of path diagrams and model comparison tools, novel visualizations for assessing reliability and validity of measurement models, and sharing capabilities for enabling collaborations.

Effects of a teacher training program on the motivation and satisfaction of history secondary students

History classes in Secondary Education form a teaching and learning space with practices that are nourished by two traditional epistemological and methodological models. To counter these models, a training program was carried out in the specialty of Geography and History of the Teacher Training Master’s aimed at changing their methodological and epistemological concepts and the design of innovative training units. The effects are evaluated through the implementation of these training units in curricular practices. This evaluation was with a pre-test and post-test formed by two scales (motivation and satisfaction). The analysis strategy was developed in two phases. In the first, the longitudinal factorial invariance is checked, progressively analyzing this invariance between the pre-test and post-test scales. In the second, a second-order growth model or factor curve is applied to assess the change in latent variables between the pre-test and the post-test. After the application of the program, a substantial increase in student motivation and satisfaction was observed. This increase was most visible in motivation, due to the low initial levels of the students.

Getting Better All the Time? An Illustrative Investigation of Multilevel Longitudinal Measurement Invariance Based on School Climate Surveys

AbstractSchool climate surveys are central to school improvement and principal evaluation policies. The quality of school climate has been linked both to student achievement and to teacher retention. Oftentimes, policymakers and practitioners are concerned with monitoring change in school climate quality in each academic year. Such applications assume longitudinal factorial invariance—it is presupposed that the surveys are measuring the same things in the same metric at each time point. While there is considerable research examining the validity of inferences based on survey‐derived climate indicators, this research is almost exclusively based on cross‐sectional data. There is little literature describing procedures for gathering evidence of factorial invariance of school climate indicators. This study proposes to adapt existing methods for evaluating factorial invariance in longitudinal designs into multilevel frameworks, and in doing so, articulates a novel method for evaluating longitudinal measurement invariance in school climate research. This technique is illustrated on a widely used school climate survey.

Development of a Combined Sensory-Cognitive Measure Based on the Common Cause Hypothesis: Heterogeneous Trajectories and Associated Risk Factors.

There is a link between sensory and cognitive functioning across old age. However, there are no integrative measures for assessing common determinants of sensory-cognitive functioning. This study aims to develop a combined measure of sensory-cognitive functioning, and to identify heterogeneous trajectories and associated risk factors. Two thousand two hundred and fifty-five individuals aged 60 years and over selected from the first six waves (2002-2012) of the English Longitudinal Study of Ageing completed a set of five self-reported visual and hearing functioning items and four cognitive items. Several health-related outcomes were also collected. The common cause model presented longitudinal factorial invariance (Tucker-Lewis index [TLI] = 0.989; Comparative Fit Index [CFI] = 0.991; Root Mean Square Error of Approximation [RMSEA] = 0.026). A common factor explained 32%, 36%, and 26% of the visual, hearing, and cognitive difficulties, respectively. The developed sensory-cognitive measure predicted incident dementia over 10 years (area under the curve = .80; 95% confidence interval [CI] = .75, .86). A three-trajectory model was proved to fit better, according to growth mixture modeling. Low levels of education and household wealth, disability, diabetes, high blood pressure, depressive symptoms, and low levels of physical activity were risk factors associated with the classes showing trajectories with a steeper increase of sensory-cognitive difficulties. A time-invariant factor explains both sensory and cognitive functioning over 8 years. The sensory-cognitive measure derived from this factor showed a good performance for predicting dementia 10 years later. Several easily identifiable socioeconomic and health-related risk factors could be used as early markers of subsequent sensory-cognitive decline. Therefore, the proposed latent measure could be useful as a cost-effective indicator of sensory-cognitive functioning.

Conflict, Closeness, and Academic Skills: A Longitudinal Examination of the Teacher–Student Relationship

The longitudinal relations between teacher–student relationship quality (TSRQ) and student achievement were examined to determine the directional associations between the quality of teacher-rated closeness and conflict with students, and measured math and reading achievement in a large, multisite sample of U.S. youth at first, third, and fifth grade. A longitudinal confirmatory factor analysis model of panel data was employed. After testing longitudinal factorial invariance across time, we tested heterogeneity in the factor variances and differences in the latent means. Math and reading achievement had longitudinal reciprocal relations. Math achievement explained small differences in subsequent teacher-rated closeness after controlling for previous levels of math achievement and teacher-rated closeness. Teacher-rated conflict served as a small but significant predictor of subsequent math achievement across measured time points but previous teacher-rated closeness did not explain subsequent reading or math achievement at any time point. Teacher-rated conflict was relatively stable across grades, whereas teacher-rated closeness varied from first to third grade. Reading and math achievement were highly stable predictors of future achievement. The findings suggested that in a lower-risk sample, measures of TSRQ and achievement may serve as predictors or outcomes and directionality of effects should not be assumed in advance.

Curve of Factors Model: A Latent Growth Modeling Approach for Educational Research.

A first-order latent growth model assesses change in an unobserved construct from a single score and is commonly used across different domains of educational research. However, examining change using a set of multiple response scores (e.g., scale items) affords researchers several methodological benefits not possible when using a single score. A curve of factors (CUFFS) model assesses change in a construct from multiple response scores but its use in the social sciences has been limited. In this article, we advocate the CUFFS for analyzing a construct's latent trajectory over time, with an emphasis on applying this model to educational research. First, we present a review of longitudinal factorial invariance, a condition necessary for ensuring that the measured construct is the same across time points. Next, we introduce the CUFFS model, followed by an illustration of testing factorial invariance and specifying a univariate and a bivariate CUFFS model to longitudinal data. To facilitate implementation, we include syntax for specifying these statistical methods using the free statistical software R.

Tracking Emotional and Behavioral Changes in Childhood: Does the Strength and Difficulties Questionnaire Measure the Same Constructs Across Time?

R. Goodman’s Strength and Difficulties Questionnaire (SDQ) is widely used to measure emotional and behavioral difficulties in childhood and adolescence. In the present study, we examined whether the SDQ measures the same construct across time, when used for longitudinal research. A nationally representative sample of parents ( N = 3,375) provided data on their children at ages 4, 5, and 6 years. Using confirmatory factor analysis (CFA) for ordinal data, two competing models (three-factor model vs. five-factor model) were tested to establish equivalence across time. Results showed that the five-factor model had a superior fit to the data compared with the alternative three-factor model which only achieved an adequate fit at a configural level. Strong longitudinal factorial invariance was established for the five-factor parent version of the SDQ. Our findings support the use of the SDQ in longitudinal studies and provide the important psychometric information required for basing educational, clinical, and policy decisions on outcomes of the SDQ.

Cross-sectional and longitudinal validation of a 13-item fatigue scale among Japanese postpartum mothers.

This study examined the psychometric properties of a 13-item fatigue scale for postpartum mothers. Japanese mothers (n = 2026) from a cohort study completed questionnaires (e.g. fatigue scale, Japanese version of the Edinburgh Postnatal Depression Scale, demographics) during their hospital stay after childbirth (baseline) and at 1, 2, 4 and 6 months postpartum. Initial factor analysis of baseline data revealed that the fatigue scale had three factors or subscales (physical, emotional and cognitive). Within-group analysis across each measurement time revealed the same three-factor structure with acceptable fit. Between-group analysis also showed longitudinal factorial invariance across time. The fatigue subscales had acceptable divergent and convergent validities with the depression scale. The subscale scores differed significantly based on participant background. The Japanese Fatigue Scale is a concise and informative tool for assessing aspects of fatigue in clinical settings and in the community.

Longitudinal factorial invariance of the Rosenberg Self-Esteem Scale: Determining the nature of method effects due to item wording

The present study contributes to the debate on the nature of wording effects (i.e., ephemeral artifacts or stable response styles) associated with the Rosenberg Self-Esteem Scale (RSES) by analysing longitudinal data (5 waves over an 8-year time span) of a non-English version of this scale from a sample of 889 French elderly. Our findings showed, first, that the RSES consists of three factors: a self-esteem factor and two method factors. Second, the measurement properties of this solution of the RSES were consistent over time. Third, the structural parameters as well as individual differences were stable, indicating that the RSES taps three meaningful and enduring individual characteristics, i.e., like personality traits. Fourth, this solution is free of any gender bias.

Developmental Changes in Executive Functioning

Although early studies of executive functioning in children supported Miyake et al.'s (2000) three-factor model, more recent findings supported a variety of undifferentiated or two-factor structures. Using a cohort-sequential design, this study examined whether there were age-related differences in the structure of executive functioning among 6- to 15-year-olds (N = 688). Children were tested annually on tasks designed to measure updating and working memory, inhibition, and switch efficiency. There was substantial task-based variation in developmental patterns on the various tasks. Confirmatory factor analyses and tests for longitudinal factorial invariance showed that data from the 5- to 13-year-olds conformed to a two-factor structure. For the 15-year-olds, a well-separated three-factor structure was found.

Investigating the factor structure and measurement invariance of phonological abilities in a sufficiently transparent language.

Theory-driven conceptualizations of phonological abilities in a sufficiently transparent language (Greek) were examined in children ages 5 years 8 months to 7 years 7 months, by comparing a set of a priori models. Specifically, the fit of 9 different models was evaluated, as defined by the Number of Factors (1 to 3; represented by rhymes, syllables, and phonemes) × Relationships Between the Latent Variables (orthogonal vs. oblique) × Level (first vs. second order). In addition, the invariant sequence of phonological abilities was examined through longitudinal factorial invariance. We administered a set of 10 phonological tasks that differed in linguistic complexity to 280 Greek-Cypriot children. Reading fluency was also assessed to externally validate the conceptualization of phonological sensitivity. The results provided evidence for the model that depicts phonological sensitivity as a unified construct that develops in an invariant structure across time and significantly predicts a child's reading performance.

Psychometric properties and longitudinal validation of the self-reporting questionnaire (SRQ-20) in a Rwandan community setting: a validation study

BackgroundThis study took place to enable the measurement of the effects on mental health of a psychosocial intervention in Rwanda. It aimed to establish the capacities of the Self-Reporting Questionnaire (SRQ-20) to screen for mental disorder and to assess symptom change over time in a Rwandan community setting.MethodsThe SRQ-20 was translated into Kinyarwanda in a process of forward and back-translation. SRQ-20 data were collected in a Rwandan setting on 418 respondents; a random subsample of 230 respondents was assessed a second time with a three month time interval. Internal reliability was tested using Cronbach's alpha. The optimal cut-off point was determined by calculating Receiver Operating Curves, using semi-structured clinical interviews as standard in a random subsample of 99 respondents. Subsequently, predictive value, likelihood ratio, and interrater agreement were calculated. The factor structure of the SRQ-20 was determined through exploratory factor analysis. Factorial invariance over time was tested in a multigroup confirmatory factor analysis.ResultsThe reliability of the SRQ-20 in women (α = 0.85) and men (α = 0.81) could be considered good. The instrument performed moderately well in detecting common mental disorders, with an area under the curve (AUC) of 0.76 for women and 0.74 for men. Cut-off scores were different for women (10) and men (8). Factor analysis yielded five factors, explaining 38% of the total variance. The factor structure proved to be time invariant.ConclusionsThe SRQ-20 can be used as a screener to detect mental disorder in a Rwandan community setting, but cut-off scores need to be adjusted for women and men separately. The instrument also shows longitudinal factorial invariance, which is an important prerequisite for assessing changes in symptom severity. This is a significant finding as in non-western post-conflict settings the relevance of diagnostic categories is questionable. The use of the SRQ-20 can be considered an alternative option for measuring the effect of a psychosocial intervention on mental health.Trial registrationNederlands Trial Register NTR1120.

Temporal relations among multidimensional perceptions of competence and trichotomous achievement goals in physical education

Objectives The purpose of the present study was two-fold: (1) To empirically establish whether young people differentiate their perceived competence in physical education (PE) in terms of the self, mastery of tasks, and others, and (2) To examine longitudinal relations between these three ways of defining perceived competence and trichotomous achievement goals. Methods At the start of the study, students ( n = 227 males, n = 205 females; M age = 13.18, SD = .87 years) completed measures of mastery-approach, performance-approach- and performance-avoidance goals, along with other-, self- and mastery-referent forms of perceived competence. The same measures were subsequently recorded three, six and nine months later. Results Analyses supported longitudinal factorial invariance for each goal and each type of perceived competence. Partial support was found for the positive influence of other-referent perceived competence on approach- and avoidance-performance goal adoption over time. Conclusion Young people can construe their competence in PE in various ways. Relative to one’s classmates, increases in other-referenced perceptions of competence can subsequently lead to increased adoption of both performance goals.

Longitudinal factorial invariance of the Maslach Burnout Inventory‐General Survey among employees with job‐related psychological health problems

AbstractThe study provides new knowledge about the longitudinal factorial invariance of the Maslach Burnout Inventory‐General Survey (MBI‐GS). In order to investigate the factor structure of the MBI‐GS and its invariance across time, a full panel data with two measurements gathered among employees with job‐related psychological health problems was used. Consistent with previous study findings, the results indicated that the correlated three‐factor model of the MBI‐GS (i.e. exhaustion, cynicism and professional efficacy) showed a better fit with the data than the alternative factor models. The correlated three‐factor structure was invariant across time, indicating that the scale has good construct validity, thus producing evidence that the MBI‐GS is a valid scale to measure job burnout. The novel finding of the study was that the professional efficacy dimension was a more central symptom of the burnout syndrome than previous research evidence among healthy employees has established. Copyright © 2011 John Wiley & Sons, Ltd.

Confirmatory Factor Analysis and Sample Invariance of the Chinese Patient Satisfaction Questionnaire (ChPSQ-9) among Patients with Breast and Lung Cancer

ObjectivesPrevious exploratory factor analysis of the 9-item Chinese Patient Satisfaction Questionnaire (ChPSQ-9) identified two dominant factors: doctor and nurse. The present study employed confirmatory factor analysis (CFA) to examine the factorial invariance of the ChPSQ-9 between and within samples of Chinese patients with breast or lung cancer. MethodsLongitudinal data were analyzed from Chinese breast and lung cancer patients who had completed the ChPSQ-9 during their first outpatient visit, at 3 months, and at 6 months after baseline. CFAs tested the fit of a one-factor model, a hierarchical model that comprised a general latent factor and two first-order factors, and a correlated model that comprised two correlated first-order factors to the data. The factorial invariance of the ChPSQ-9 between six independent samples across time was investigated using multigroup CFAs. ResultsThe CFA's results demonstrated a better fit of the correlated model over the one-factor model and the hierarchical model in the breast and lung cancer samples. The correlated model showed evidence of cross-sample and longitudinal factorial invariance. Patients were generally satisfied with services provided by doctors and nurses. Internal consistency of the scale was also good for both cancer samples across time. ConclusionsThe ChPSQ-9 is a valid and reliable instrument to be employed among breast and lung cancer patients, in clinical settings or intervention research, to evaluate group differences in patient satisfaction and its association with intervention effectiveness.

Longitudinal factorial invariance of the PedsQL™ 4.0 Generic Core Scales Child Self-Report Version: One year prospective evidence from the California State Children’s Health Insurance Program (SCHIP)

The measurement of health-related quality of life (HRQOL) in pediatric medicine and health services research has grown significantly over the past decade. The paradigm shift toward patient-reported outcomes (PROs) has provided the opportunity to emphasize the value and critical need for pediatric patient self-report. In order for changes in HRQOL/PRO outcomes to be meaningful over time, it is essential to demonstrate longitudinal factorial invariance. This study examined the longitudinal factor structure of the PedsQL 4.0 Generic Core Scales over a one-year period for child self-report ages 5-17 in 2,887 children from a statewide evaluation of the California State Children's Health Insurance Program (SCHIP) utilizing a structural equation modeling framework. Specifying four- and five-factor measurement models, longitudinal structural equation modeling was used to compare factor structures over a one-year interval on the PedsQL 4.0 Generic Core Scales. While the four-factor conceptually-derived measurement model for the PedsQL 4.0 Generic Core Scales produced an acceptable fit, the five-factor empirically-derived measurement model from the initial field test of the PedsQL 4.0 Generic Core Scales produced a marginally superior fit in comparison to the four-factor model. For the five-factor measurement model, the best fitting model, strict factorial invariance of the PedsQL 4.0 Generic Core Scales across the two measurement occasions was supported by the stability of the comparative fit index between the unconstrained and constrained models, and several additional indices of practical fit including the root mean squared error of approximation, the non-normed fit index, and the parsimony normed fit index. The findings support an equivalent factor structure on the PedsQL 4.0 Generic Core Scales over time. Based on these data, it can be concluded that over a one-year period children in our study interpreted items on the PedsQL 4.0 Generic Core Scales in a similar manner.

Factor Structure and Longitudinal Invariance of the Maslach Burnout Inventory

Objective: The study examined the factorial validity of the Maslach Burnout Inventory (MBI) for social work research and practice. Method: Factor structure and longitudinal invariance of the MBI were tested using structural equation modeling techniques with a random sample of 475 state-registered social workers in California. Results: The original three-factor model was superior over other competing factor models. Investigation of the second-order factor model supported the presence of the common burnout factor and indicated depersonalization and emotional exhaustion were core components of burnout. Longitudinal factorial invariance was not achieved for personal accomplishment. Conclusion: The findings suggest the applicability of the MBI in a longitudinal research with careful inference regarding personal accomplishment and highlight the importance of depersonalization in social worker burnout.