Factorial Validity and Invariance of a Survey Measuring Psychosocial Correlates of Colorectal Cancer Screening in Ontario, Canada—A Replication Study (original) (raw)
Related papers
Quality of Life Research, 2007
Introduction The European Organisation for Research and Treatment of Cancer (EORTC) QLQ-C30 is a widely used health-related quality of life instrument. The main aim of this study is to investigate whether there are international differences in response to the questionnaire that can be explained by cultural factors. Methods Analyses involved a database of 106 separate studies including data from over 28,000 respondents. Differential item functioning (DIF) analyses using logistic regression were conducted for each item of the EORTC QLQ-C30 with respect to cultural/geographic group. Results were qualitatively compared with previously reported DIF analyses by translation to explore whether the source of the DIF was more likely to be linguistic or cultural in nature. Results Although most response patterns were similar, there were a number of international differences in how the questionnaire was answered. The largest variations were found in the results for Eastern Europe and East Asia. Results for the UK, the US and Australia tended to be similar. Many of the European results followed patterns that were more clearly explained when grouped by translation than when grouped by geographical region. Discussion Our results suggest that, in general, the EORTC QLQ-C30 is suitable for use in a wide variety of countries and settings. Some response variations that have the potential to affect the results of international studies were identified, but it was not always clear whether the source of the variation was primarily linguistic or cultural.
Guidelines for the Process of Cross-Cultural Adaptation of Self-Report Measures
International Workshop on Model Checking of Software, 2000
With the increase in the number of multinational and multicultural research projects, the need to adapt health status measures for use in other than the source language has also grown rapidly. 1,4,27 Most questionnaires were developed in English-speaking countries, 11 but even within these countries, researchers must consider immi- grant populations in studies of health, especially when their exclusion could
International Journal of Clinical and Health Psychology, 2004
We wished to assess both the factor structure and the reliability of the 28-item version of the General Health Questionnaire (GHQ-28) in a non-clinical population in El Salvador. The GHQ-28 was applied to a large sample (n = 714) of university students in El Salvador. A principal components analysis was applied and a four-factor solution selected. A subgroup of the participants were retested after an average of 3 months to assess retest reliability while internal consistency was assessed using the Cronbach's alpha test. The factor analysis results corresponded closely to the original factor structure, though with a relatively higher inter-correlation found between the resulting scales, especially the 'anxiety and insomnia' and 'somatization' scales. The test-retest and internal consistency measures reached values .70 or higher in each case. The findings indicate a remarkable consistency in the factor structure of the GHQ-28 with result from other cultural settings, supporting Goldberg's hypothesis of a common language of psychological distress between cultures. The 'severe depression' and 'social dysfunction' scales appear to be relatively stable and independent while the 'anxiety and insomnia' and 'somatization' scales are more highly correlated. The reliability of the instrument in El Salvador is satisfactory. KEYWORDS. General Health Questionnaire (GHQ-28). University sample. Factor analysis. Reliability Instrumental study. PALABRAS CLAVE. Cuestionario de Salud General (GHQ-28). Muestra universitaria. Análisis factorial. Confiabilidad. Estudio instrumental. RESUMO. Quisemos avaliar tanto a estrutura factorial como a fiabilidade da versão de 28 itens do Questionário de Saúde Geral (GHQ-28) numa amostra clínica em El Salvador. Aplicámos o GHQ-28 a uma amostra de 714 de alunos universitários em El Salvador. Utilizámos uma análise de componentes principais e seleccionámos una solução de 4 factores. Reaplicámos a prova a um grupo de participantes de pois de uma média de 3 meses, para avaliar a fidelidade de reteste do instrumento e calculámos a fidelidade interna do GHQ-28 através da prova alpha de Cronbach. Os resultados da análise factorial corresponderam estreitamente à estrutura factorial anteriormente identificada, ainda que tivéssemos encontrado uma correlação mais alta entre as escalas, sobretudo entre Ansiedade e insónia e Somatização. A fidelidade teste-reteste e a consistência interna alcançaram valores de 0,70 ou superiores. Os resultados da análise factorial indicam uma grande coincidência com as conclusões de outros meios culturais, o que apoia a hipótese de Goldberg de que há uma forma comum de comunicar angústia psicológica em culturas distintas. As escalas de Depressão severa e de Disfunção social parecem ser relativamente estáveis e independentes, enquanto que as de Ansiedade e insónia e de Somatização se correlacionam mais. A fidelidade do instrumento é satisfatória.
Assessing cross-cultural validity of scales: A methodological review and illustrative example
International Journal of Nursing Studies, 2008
In this article, we assessed the cross-cultural validity of the Women's Role Strain Inventory (WRSI), a multi-item instrument that assesses the degree of strain experienced by women who juggle the roles of working professional, student, wife and mother. Cross-cultural validity is evinced by demonstrating the measurement invariance of the WRSI. Measurement invariance is the extent to which items of multi-item scales function in the same way across different samples of respondents. We assessed measurement invariance by comparing a sample of working women in Taiwan with a similar sample from the United States. Structural equation models (SEMs) were employed to determine the invariance of the WRSI and to estimate the unique validity variance of its items. This article also provides nurseresearchers with the necessary underlying measurement theory and illustrates how SEMs may be applied to assess crosscultural validity of instruments used in nursing research. Overall performance of the WRSI was acceptable but our analysis showed that some items did not display invariance properties across samples. Item analysis is presented and recommendations for improving the instrument are discussed. r
Journal of Affective Disorders, 2013
Body dissatisfaction and eating disorder rates have increased in racial and ethnic minority groups, yet the validity of various commonly-used eating disorder instruments has not been established in these populations. One way to establish validity is to test for measurement invariance; namely, that the same constructs are being measured across groups. This study tested the measurement invariance of the Eating Disorder Examination Questionnaire (EDE-Q) across non-Hispanic White and Hispanic women. Method: Female undergraduates (n = 561) were recruited from a southwestern U.S. university. Confirmatory factor analysis (CFA) and measurement invariance of the EDE-Q were tested in non-Hispanic White and Hispanic samples. Results: CFA analyses revealed that the original four-factor structure did not fit the data in either group. Only a modified 7-item, three-factor structure of the EDE-Q provided an acceptable fit in both non-Hispanic White and Hispanic women. Thus, this modified EDE-Q factor structure was used to test the equivalence of the measure between groups. Results found that the factor structure was similar across groups, but the factor loadings and intercepts differed across non-Hispanic White and Hispanic women. Discussion: A modified 7-item, three-factor structure of the EDE-Q provided an acceptable fit of the data, which is supported by previous research. However, the lack of measurement invariance suggests that researchers should be cautious when using this modified EDE-Q to make explicit comparisons between non-Hispanic White and Hispanic women. Future research should further examine the psychometric properties of the EDE-Q in ethnically diverse groups, specifically the role of dietary restraint among Hispanic women.
PLOS ONE
Objective Analyze the measurement invariance and the factor structure of the Patient Health Questionnaire-9 (PHQ-9) in the Peruvian population. Method Secondary data analysis performed using cross-sectional data from the Health Questionnaire of the Demographic and Health Survey in Peru. Variables of interest were the PHQ-9 and demographic characteristics (sex, age group, level of education, socioeconomic status, marital status, and area of residence). Factor structure was evaluated by standard confirmatory factor analysis (CFA), and measurement invariance by multi-group CFA, using standard goodness-of-fit indices criteria for interpreting results from both CFAs. Analysis of the internal consistency (α and ω) was also pursued. Results Data from 30,449 study participants were analyzed, 56.7% were women, average age was 40.5 years (standard deviation (SD) = 16.3), 65.9% lived in urban areas, 74.6% were married, and had 9 years of education on average (SD = 4.6). From standard CFA, a one-dimensional model presented the best fit (CFI = 0.936; RMSEA = 0.089; SRMR = 0.039). From multi-group CFA, all progressively restricted models had ΔCFI<0.01 across almost all groups by demographic characteristics. PHQ-9 reliability was optimal (α = ω = 0.87).
Testing measurement invariance across groups: Applications in crosscultural research
International Journal of Psychological Research, 2010
Researchers often compare groups of individuals on psychological variables. When comparing groups an assumption is made that the instrument measures the same psychological construct in all groups. If this assumption holds, the comparisons are valid and differences/similarities between groups can be meaningfully interpreted. If this assumption does not hold, comparisons and interpretations are not fully meaningful. The establishment of measurement invariance is a prerequisite for meaningful comparisons across groups. This paper first reviews the importance of equivalence in psychological research, and then the main theoretical and methodological issues regarding measurement invariance within the framework of confirmatory factor analysis. A step-by-step empirical example of measurement invariance testing is provided along with syntax examples for fitting such models in LISREL.
Arthritis and Rheumatism, 2004
ObjectiveGuidelines have been established for cross-cultural adaptation of outcome measures. However, invariance across cultures must also be demonstrated through analysis of Differential Item Functioning (DIF). This is tested in the context of a Turkish adaptation of the Health Assessment Questionnaire (HAQ).Guidelines have been established for cross-cultural adaptation of outcome measures. However, invariance across cultures must also be demonstrated through analysis of Differential Item Functioning (DIF). This is tested in the context of a Turkish adaptation of the Health Assessment Questionnaire (HAQ).MethodsInternal construct validity of the adapted HAQ is assessed by Rasch analysis; reliability, by internal consistency and the intraclass correlation coefficient; external construct validity, by association with impairments and American College of Rheumatology functional stages. Cross-cultural validity is tested through DIF by comparison with data from the UK version of the HAQ.Internal construct validity of the adapted HAQ is assessed by Rasch analysis; reliability, by internal consistency and the intraclass correlation coefficient; external construct validity, by association with impairments and American College of Rheumatology functional stages. Cross-cultural validity is tested through DIF by comparison with data from the UK version of the HAQ.ResultsThe adapted version of the HAQ demonstrated good internal construct validity through fit of the data to the Rasch model (mean item fit 0.205; SD 0.998). Reliability was excellent (α = 0.97) and external construct validity was confirmed by expected associations. DIF for culture was found in only 1 item.The adapted version of the HAQ demonstrated good internal construct validity through fit of the data to the Rasch model (mean item fit 0.205; SD 0.998). Reliability was excellent (α = 0.97) and external construct validity was confirmed by expected associations. DIF for culture was found in only 1 item.ConclusionsCross-cultural validity was found to be sufficient for use in international studies between the UK and Turkey. Future adaptation of instruments should include analysis of DIF at the field testing stage in the adaptation process.Cross-cultural validity was found to be sufficient for use in international studies between the UK and Turkey. Future adaptation of instruments should include analysis of DIF at the field testing stage in the adaptation process.