Testing Factorial Invariance Research Articles

Longitudinal changes in coping strategies across midlife and older adulthood: findings from the midlife in the United States study.

Most studies examining age differences in coping across adulthood come from cross-sectional studies and focus on the broader categories of problem- and emotion-focused coping. We aimed to establish a factor structure for coping items used in a national, longitudinal study of aging (MIDUS) and examine age patterns in coping strategies over 10 years. We performed exploratory and confirmatory factor analysis, and factorial invariance testing. Next we conducted a series of multilevel models for each coping factor with participants from waves II and III of the MIDUS study (N = 2,661, Mage = 55, 58% women, 84% White). We found a four-factor solution: instrumental action; denial/disengagement; positive reappraisal; focus and venting of emotions. Invariance was established across time and age. At baseline, age was positively associated with the use of three strategies, though younger adults used more focus and venting of emotions. There was an overall decrease over 10 years in use of all strategies, which was moderated by age. Positive reappraisal declined more steeply among midlife participants, whereas the remaining strategies declined more for older participants. Results highlight the multi-dimensionality of MIDUS coping items and underscores the import of age in understanding changes in coping across midlife and older adulthood.

Factorial invariance of the Wechsler Intelligence Scale for Children, Fifth Edition, across the UK, US and Australia & New Zealand.

This study examined the factorial invariance of the factor structure of the Wechsler Intelligence Scale for Children, Fifth Edition (WISC-V) across the UK, US and Australia & New Zealand (A&NZ). The factorial equivalence of cognitive assessments should be demonstrated before assuming cross-culture generalizability and interpretations of score comparisons. Data were obtained from the UK, US and A&NZ normative standardizations of the WISC-V. The samples consisted of 415 UK, 2200 US and 528 A&NZ children, aged 6-16. Confirmatory factor analysis was applied separately in each sample to establish the baseline model. Next, tests of factorial invariance were undertaken using the recommended hierarchical approach, firstly across the UK and A&NZ samples and then across the UK and US samples. The five-factor first-order scoring model was found to be excellent fit across all three samples independently. Strict factorial invariance of the WISC-V was demonstrated firstly across the UK and A&NZ and secondly the UK and US nationally representative standardization samples. Comparison of latent means found small but significant differences in female children across the UK and A&NZ samples. Consistent with previous research, these results demonstrate the generality of the WISC-V factor structure across the UK, US and A&NZ. Furthermore, as the WISC-V factor structure aligns with the Cattell-Horn-Carroll (CHC) model of cognitive abilities, the results add further support to the cross-cultural generalizability of the CHC model. Small but significant differences in latent factor scores found across samples support the development and use of local normative data.

Stockholm Syndrome and Gender-Related Ideologies and Attitudes: A Psychometric Assessment

Stockholm syndrome, a paradoxical phenomenon, characteristic of the particular psychological functioning of people in captivity and victims of mistreatment, sexual abuse and gender-based violence, arouses significant interest in psychological sciences. However, the related instrumentation remains limited, due to the fact that there is not a significant number of measurements that can evaluate it. In addition, the current main measure (the <i>scale for identifying “Stockholm Syndrome” reactions in young dating women/Escala para identificar reacciones de síndrome de Estocolmo (SISSR) relacionada con violencia de pareja</i>), only exists in the English and Spanish languages; which constitutes a linguistic obstacle for its administration to individuals who speak other languages, such as French. However, the simple translation of the items of a measurement does not guarantee its reliability from a psychometric point of view. In this vein, this study proposes the translation in French and validation of the Spanish version of this measure. It also proposes, as part of testing the predictive validity of the measure, to link the construct of Stockholm syndrome with gender-related ideologies and attitudes. The validation of the French version of the Stockholm syndrome measurement scale was carried out with two samples (N = 836) consisting entirely of women. The exploratory test (EFA) carried out with 400 participants reveals a reliable tri-factorial structure of 16 elements, after the elimination of 33 elements, due to factor loadings lower than .40. The confirmatory analysis of this factorial structure, using the Structural Equation Method (CFA-SEM), carried out on a sample of 436 participants, supports the tri-factorial structure which fits the data better. Tests of factorial invariance of the measurement, depending on marital status (n1 = 215 married women; n2 = 221 concubine) reveal a structural equivalence between the groups. The predictive validity of the measure reveals that Stockholm syndrome is linked to attitudes towards gender-based violence, sexism, feminism, non-justification of the gender system and gender-based social dominance.

The Short Version of the Italian Maastricht Vital Exhaustion Questionnaire (MVEQ): Psychometric Properties and Relationships with Anxiety, Depression, and Stress in a Community Sample of Older Adults

Vital Exhaustion (VE) refers to a physical and mental state of excessive fatigue, feelings of demoralization, hopelessness, and increased irritability. The short form of the Maastricht Vital Exhaustion Questionnaire (MVEQ) is a widely used measure to assess VE. Despite its utility is broadly recognized, the validity and reliability of the scale have yet to be examined in the Italian context. The present study aimed to evaluate the psychometric properties of the shortened MVEQ in a community sample of Italian older adults. A total of 722 older adults (Mage = 72.97, SD = 7.71; 60.4% females) completed the MVEQ, as well as other self-report questionnaires assessing anxiety, depression and stress in order to evaluate the criterion-related validity of the scale. A confirmatory factor analysis (CFA) was conducted to examine the original MVEQ latent structure. Internal consistency was assessed through model-based omega coefficient. Test-retest reliability was examined by re-administering the MVEQ after three months to a subsample of 568 participants. Factorial invariance tests across gender were conducted by means of multi-group CFAs. The one-factor model showed an acceptable fit to the data. The MVEQ yielded a reliable total score (ω = 0.822) and showed moderate-to-large correlations with measures of anxiety, depression, and stress (r range 0.30 to 0.75, ps < 0.001). Test-retest reliability was supported by an Intraclass Correlation Coefficient (ICC) of 0.661. Lastly, the scale was factorially invariant across gender. Overall, the MVEQ provided evidence of reliability and criterion-related validity in a sample of Italian older adults and may be useful for both clinical and research practices.

Testing the Psychometric Properties of the Challenging Parent Standard Questionnaire (CPSQ) in the Italian Educational Context

The Challenging Parent Standard Questionnaire (CPSQ) is a measurement tool aimed at surveying the field of parent-teacher relationships to assess the frequency of challenging parental behaviours as well as the occupational stress experienced by teachers in response to those behaviours.The present study examined the factor structure and the main psychometric properties of the CPSQ in a sample of Italian in-service primary and lower secondary teachers (N = 1,025). In order to investigate the most appropriate factor structure for the Italian version of the questionnaire, researchers compounded three different factor retention methods: K1 rule (Kaiser, 1960), scree test (Cattel, 1966) and parallel analysis (Horn, 1965).The results show a practical and robust five-factor measurement model describing the challenging behaviours of parents: ‘Excessively worried about education’, ‘Unsatisfied’, ‘Uncooperative’, ‘Overprotective’ and ‘Uninvolved’.In Italian primary and lower secondary schools, the CPSQ factor pattern partially differs from the pattern found in studies conducted in different educational contexts (i.e., Lambert &amp; McCarthy, 2006; Van der Wolf &amp; Everaert, 2005). Recommendations for a more accurate factor retention process in testing factorial invariance in measurement tools are discussed.

영과잉 자료의 측정동일성 검증

Multi-group confirmatory factor analysis (MGCFA) is a common tool for testing factorial invariance within structural eqaution modeling (SEM) framework; however, a two-part factor model might be more appropriate for zero-inflated measures due to the severe non-normality of the data. Nevertheless, testing the factorial invariance of zero-inflated variables using the two-part factor model is uncommon. To fill that gap in the literature, the current study demonstrated the use of two-part factor model for testing factorial invariance of highly zero-inflated measures and compared the result to the MGCFA’s. The two models led to different factorial invariance results on the zero-inflated measures. The two-part factor model supported full scalar invariance of the continuous-part model whereas the MGCFA concluded only partial metric invariance. Thus, applying a different factor model brought different conclusions about factorial invariance when the measures were zero-inflated.

Cross-cultural adaptation and psychometric properties of the Italian version of the Orthorexia Nervosa Inventory (ONI)

BackgroundOrthorexia Nervosa (ON) is an emerging clinical condition characterized by a pathological fixation with healthy eating. Recently, the Orthorexia Nervosa Inventory (ONI) has emerged as a promising tool for assessing orthorexic tendencies and behaviours, aiming to overcome the well-established limitations of existing measures for ON. The present study aimed to examine the psychometric properties of the Italian version of the ONI.MethodsA total of 879 participants (Mage = 33.22 years, SD = 9.19; 56.9% females) completed the ONI along with the Düsseldorf Orthorexia Scale (DOS), measures of disordered eating, obsessive-compulsive symptoms (OCD), and psychosocial impairment. To establish the factorial validity of the ONI, a competing measurement modeling approach was employed by comparing standard confirmatory factor analytic (CFA) with exploratory structural equation modeling (ESEM) solutions. Model-based omega coefficients were computed to examine the internal consistency of the scale. Factorial invariance tests across gender were conducted within a multi-group framework.ResultsA three-factor first-order ESEM solution provided the best and most parsimonious representation of the data: χ2(207) = 558.641, p < .001, RMSEA = 0.044 (90% CI 0.040–0.048), CFI = 0.976, TLI = 0.968, SRMR = 0.036. The three latent dimensions, labelled behaviors, emotions, and impairments, showed excellent internal consistency (ω > 0.88). Furthermore, ONI scores were found to be positively correlated with DOS scores, disordered eating, OCD symptoms, and psychosocial impairment, supporting its convergent and criterion validity. Eventually, the ONI was factorially invariant across gender.ConclusionsOverall, the present study provides evidence for the satisfactory psychometric properties of the ONI in the Italian context, endorsing its use in both clinical and research settings.

The Pain Anxiety Symptom Scale: Initial Development and Evaluation of 4 and 8 Item Short Forms

Elevated levels of anxiety in relation to chronic pain have been consistently associated with greater distress and disability. Thus, accurate measurement of pain-related anxiety is an important requirement in modern pain services. The Pain Anxiety Symptom Scale (PASS) was introduced over 30 years ago, with a shortened 20-item version introduced 10 years later. Both versions of the PASS were derived using Principal Components Analysis, an established method of measure development with roots in classical test theory. Item Response Theory (IRT) is a complementary approach to measure development that can reduce the number of items needed and maximize item utility with minimal loss of statistical and clinical information. The present study used IRT to shorten the 20-item PASS (PASS-20) in a large sample of people with chronic pain (N = 2,669). Two shortened versions were evaluated, 1 composed of the single best-performing item from each of its 4 subscales (PASS-4) and the other with the 2 best-performing items from each subscale (PASS-8). Several supplementary analyses were performed, including comparative item convergence evaluations based on sample characteristics (ie, female or male sex; clinical or online sample), factor invariance testing, and criterion validity evaluation of the 4, 8, and 20-item versions of the PASS in hierarchical regression models predicting pain-related distress and interference. Overall, both shortened PASS versions performed adequately across these supplemental tests, although the PASS-4 had more consistent item convergence between samples, stronger evidence for factor invariance, and accounted for 83% of the variance accounted for by the PASS-20% and 92% of the variance accounted for by the PASS-8 in criterion variables. Consequently, the PASS-4 is recommended for use in situations where a briefer evaluation of pain-related anxiety is appropriate. PerspectiveThe Pain Anxiety Symptom Scale (PASS) is an established measure of pain-related fear. This study derived 4 and 8-item versions of the PASS using IRT. Both versions showed strong psychometric properties, stability of factor structure, and relation to important aspects of pain-related functioning.

Measurement Invariance of Scores on the Somatic Symptom Scale-8: National Sample of Non-Clinical Adults in the United States

Objective The aim of the present study was to test the factorial invariance and convergent validity evidence of scores on the Somatic Symptom Scale (SSS)-8 with a national sample of adults living in the United States. Method A data collection contracting service was hired to recruit a national, non-clinical sample (N = 821) of adults in the United States stratified by the census data for age, gender, ethnicity, and geographic location. Results Factorial invariance testing via multiple-group confirmatory factor analysis revealed strong factorial invariance evidence (configural, metric, and scalar) of SSS-8 scores across gender, ethnicity, help-seeking history, education, and income. Convergent validity testing displayed strong correlations between SSS-8 scores and the following established measures: Patient Health Questinaire-9, Generalized Anxiety Disorder-7, and Mental Health Inventory-5. Conclusion Collectively, the results suggest that professional counselors can use the SSS-8 to enhance somatic symptomology screening efforts with adults living in the United States.

An Online Survey Testing Factorial Invariance of the Optimization in Primary and Secondary Control Scales among Older Couples in Japan and the US.

This study examines the factorial invariance of the Optimization in Primary and Secondary Control (OPS) scale and its associations with subjective well-being among older couples in Japan and the US. To this end, 200 older couples in Japan and 220 in the US were recruited through paid vendors and completed the questionnaire online. Couples were eligible if husbands were 70 years or older and wives were 60 years or older. A six-factor model, in which Compensatory Primary Control was subdivided into two factors, fit the data best; its factorial invariance was confirmed among the four subsamples. Compensatory Secondary Control was more strongly associated with subjective well-being in American couples than in Japanese couples, although the associations between well-being and the other five OPS factors were similar in the two countries. Future research on this six-factor model will be able to examine how these control strategies function in different cultures.

A patient-reported experience measure for community pharmacy including development of a short-form: The perceived service quality scale.

The perceived service quality scale (pSQS) is a patient-reported experience measure (PREM) previously developed for measuring perceived service quality (pSQ) in community pharmacies. While measuring pSQ is feasible, further psychometric evaluation of the pSQS is warranted. In addition, the length of the 20-item pSQS may lead to fatigue among patients. It remains to be determined whether a short form of the pSQS has acceptable psychometric properties. The aim of this study was to psychometrically test the pSQS with a specific focus on making scoring recommendations and developing a short form pSQS with acceptable psychometric properties. Participants were recruited either in community pharmacies or via an online panel to complete a questionnaire including the pSQS. Confirmatory factor analyses (CFA) were conducted using robust statistics, including tests of factorial invariance. Alternative models were tested including a bifactor model. Spearman's correlation was used to conduct test-retest analyses on responses obtained one month apart. Data were analysed from 319 participants recruited in-store and 303 participants recruited online, 86 participants providing test-retest reliability. Tests of factorial invariance indicated that the pSQS is stable across settings. The most parsimonious and best-fitting solution was obtained with a 19-item bifactor model with 5 factors plus a "general" factor. Factor scores obtained from the "general" factor explained sufficient variance and are unlikely to be excessively biased in regression models. A short-form 6-item scale (pSQ-SF6) demonstrated acceptable psychometric properties and similar predictive capacity to the original pSQS for patient loyalty intentions. Test-retest analyses indicated acceptable reliability for pSQS and PSQ-SF6. This study confirms that the pSQS has acceptable psychometric properties including temporal stability. It is recommended that a 19-item pSQS be used to obtain a comprehensive overview of patients' pSQ. The short-form pSQ-SF6 is suitable as a community pharmacy PREM.

Psychological Well-Being Increment as Post-Traumatic Growth in Women with Breast Cancer: A Controlled Comparison Design Using Propensity Score Matching.

The aim of this study was to confirm post-traumatic growth with respect to the psychological well-being of women with breast cancer compared to women without disease. Propensity score was used to match the two groups according to age, religious beliefs, education level, monthly income, and marital status. A psychological well-being scale with six factors was used, including positive relations with others (PR), autonomy (AU), environmental mastery (EM), personal growth (PG), purpose in life (PL), and self-acceptance (SA). A total 178 women with vs. 178 women without breast cancer were compared by matching with propensity scores, using factorial invariance tests to reduce measurement errors. The results showed that women with breast cancer had significantly higher psychological well-being for all the six factors (Δχ2 = 37.37, p < 0.001) and higher variability in terms of PR, AU, and PL than women without breast cancer (Δχ2 = 45.94, p < 0.001). Furthermore, women with breast cancer exhibited a significantly higher association between PG and PL and a significantly lower association between PG and EM than women without breast cancer (Δχ2 = 44.49, p < 0.001). This implies that psychological well-being could assess broader and more subtle post-traumatic growth in women with breast cancer and that growth was more associated with internal life value than with external environmental control.

The Impact and Detection of Uniform Differential Item Functioning for Continuous Item Response Models.

Psychometricians have devoted much research and attention to categorical item responses, leading to the development and widespread use of item response theory for the estimation of model parameters and identification of items that do not perform in the same way for examinees from different population subgroups (e.g., differential item functioning [DIF]). With the increasing use of computer-based measurement, use of items with a continuous response modality is becoming more common. Models for use with these items have been developed and refined in recent years, but less attention has been devoted to investigating DIF for these continuous response models (CRMs). Therefore, the purpose of this simulation study was to compare the performance of three potential methods for assessing DIF for CRMs, including regression, the MIMIC model, and factor invariance testing. Study results revealed that the MIMIC model provided a combination of Type I error control and relatively high power for detecting DIF. Implications of these findings are discussed.

A validation study of the Italian version of the Attitudes Toward Obese Persons (I-ATOP) questionnaire

ObjectivesWeight bias is defined as negative attitudes towards, and beliefs about, others because of their weight. Like other forms of stigma, weight stigma has a harmful impact on health, including depressive symptoms, disordered eating, body image disturbances and poor quality of life. Several instruments measuring weight-related attitudes have been developed, such as the Attitudes Toward Obese Persons (ATOP). The purpose of this study was to test the psychometric properties of the Italian version of the ATOP (I-ATOP). MethodsThe ATOP was adapted into Italian following the back-translation procedure. A total of 800 participants (Mage=31.40; 54.9% females) completed the I-ATOP alongside the Weight Bias Internalization Scale (WBIS). Exploratory factor analysis (EFA) was conducted on half of the sample, while the remaining half was selected to cross-validate the resulting solution via confirmatory factor analysis (CFA). Factorial invariance tests across gender were computed using multi-group CFA. ResultsEFA suggested a one-factor structure with four items excluded due to their low standardised loadings. The trimmed model was cross-validated showing an acceptable fit to the data: MLRχ2 = 159.467 (df=81); RMSEA= 0.049; CFI= 0.939; TLI= 0.910; SRMR= 0.046. An omega coefficient of 0.818 confirmed the strong reliability of the I-ATOP. Convergent validity was demonstrated by a significant and moderate correlation with the WBIS. Configural, metric, and scalar invariance across gender were established. ConclusionsI-ATOP demonstrated to be a valid and reliable instrument useful for both clinical and research practices, as well as to support the development of educational and therapeutic actions able to reduce the stigma among the general public.

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.

The subcomponents of affect scale (SAS): validating a widely used affect scale

Objective There is a need for a brief affect scale that also encompasses different components of affect relevant for researchers interested in physiological and health outcomes. The Subcomponents of Affect Scale (SAS) meets this need. This 18-item scale has nine positive and nine negative affect items encompassing six subscales (calm, well-being, vigour, depression, anxiety, anger). Previous research using the SAS has demonstrated its predictive validity, but no work has tested its subscale structure or longitudinal validity. Design Data from the Common Cold Project in which individuals (N = 610) completed the SAS over the course of seven days were used. Results Confirmatory factor analysis demonstrated the reliability of the subscale structure of the SAS across seven days (positive affect subscale structure: CFIs ≥ 0.98; negative affect subscale structure: CFIs ≥ 0.94 with day 6 CFI = 0.91) and tests of factorial invariance showed the scale is valid to use over time. Conclusions These results confirm the psychometric validity of the subscale structure of the SAS and imply that the subscales can be used longitudinally, allowing for its use in health research as well as non-health research that can benefit from its subscale structure and longitudinal capabilities.

Cross‐cultural validation of the Turkish version of SCORE‐15

AbstractThe purpose of the current study was to examine the validity and reliability of the fifteen‐item Systemic Clinical Outcome and Routine Evaluation (SCORE‐15) Turkish version. The suggested three‐factor structure was confirmed with a total sample of 327 participants including both community and clinical samples. The results of factorial invariance tests demonstrated that the structure of the scale was consistent across both gender and community/clinical groups. Furthermore, discriminant validity was supported by negative correlations with marital satisfaction, life satisfaction and general family functioning as lower scores in SCORE‐15 reflect better adjustment. Furthermore, results showed that SCORE‐15 has good internal consistency reliability and significantly differentiates between community and clinical samples. Overall, these findings indicate that the Turkish version of SCORE‐15 is a valid and reliable instrument that can be used for assessing family functioning in routine clinical practice and family therapy research. Practitioner points SCORE‐15 is a brief and effective instrument for assessing overall family functioning with specific dimensions of family strengths, communication and difficulties The Turkish version of SCORE‐15 exhibited similar factorial properties across gender and community/clinical groups The Turkish version of SCORE‐15 can be used in both clinical and community contexts for research and intervention

Psychometric properties of the Sleep Hygiene Index in a large Italian community sample

Objective/backgroundPoor sleep hygiene is considered an exacerbating and perpetuating factor of sleep disturbances and is also associated with poor mental health. The Sleep Hygiene Index (SHI) is a self-report measure assessing adherence to sleep hygiene practices. The aim of this study was to estimate the psychometric properties of the SHI in an Italian representative sample of the general population, following a formative measurement approach. Patients/methodsParticipants (n = 6276; M = 33.62, SD = 13.45) completed the SHI alongside measures of sleep disturbance, depression, anxiety, and stress. To consider the item formative nature, sets of item-composites weighted by means of canonical correlation analysis was created and a confirmatory factor analysis (CFA) was implemented. Factorial invariance tests were computed considering both presence of sleep problems and presence of emotional distress symptoms as grouping variables. Results and conclusionsCFA confirmed the unidimensional structure of SHI. Internal consistency was acceptable (ω = 0.752). Test-retest reliability at 8–10 months presented an ICC of 0.666. SHI significantly correlated with sleep, depression, anxiety and stress symptoms (r range from 0.358 to 0.500). Configural and metric invariance were reached for both grouping variables. Partial scalar invariance was obtained only across emotional distress groups. People with emotional symptoms reported higher latent means on the sleep hygiene dimension. Findings support the validity and reliability of the Italian version of the SHI. Importantly, the SHI showed robust psychometric properties both in healthy individuals and in individual reporting mental health symptoms. Thus, it is advisable to use this version of the SHI in both research and clinical practice.

Modification of the Rosenberg Scale to Assess Self-Esteem in Children.

Rosenberg's scale (RSES) is widely used to assess global self-esteem (SE) in adults and adolescents but is not validated for children <12 years. This study assessed the internal consistency, convergent validity, and factor structure of a modified RSES for schoolchildren (CRSES) aged 7–12 years. A total of 711 children aged 9.0 ± 1.5 years completed the CRSES; a subset (n = 417) also completed a life satisfaction (LS) scale. Data were submitted for confirmatory factor analysis (CFA) and tests of factorial invariance by sex. Two-way ANOVA compared scores by age-group and sex; whilst Pearson's correlations examined the relationship between LS and SE. Following the use of modification indices the fit for the global SE model met the goodness of fit statistic criteria: χ(27, n = 711) = 77.22; χnormed = 2.860 CFI = 0.961; RMSEA = 0.051 with 90% CI = 0.038-0.065; SRMR = 0.037; and displayed respectable internal consistency (α = 0.79). The model was also factorially invariant by sex. SE scores did not vary sex (p > 0.05); but were significantly reduced in children aged 9–10 and 11–12 years compared to children aged 7–8 years. The global SE score was significantly correlated (r = 0.51; P < 0.001) with LS. The current version of the CRSES can reliably examine global SE in children aged 7–12 years; extending the use of the RSES to allow tracking across the life course.

Faktorijalna invarijantnost u longitudinalnim studijama - merenje istog konstrukta tokom vremena

When researchers are conducting studies that require repeated measures, it is not uncommon for them to assume that the particular instrument is equally going to assess the latent construct of interest no matter how many times the instrument (test) is administered. In other words, it is not in question whether the properties of the test are likely to change or not. However, measurement invariance is not something that the instrument possesses by default. Measurement invariance has to be tested. The aim of this paper was to provide an insight into testing factorial invariance performing the confirmatory factor analysis on a set of longitudinal data. The first part of this paper is theoretical and describes different forms of invariance. The second part offers a concrete example and a step-by-step guide on how to perform confirmatory factor analysis for repeated measurements to test the invariance using statistical software R.