Mean and Covariance Structures (MACS) Analyses of Cross-Cultural Data: Practical and Theoretical Issues

Little, Todd D.

doi:10.1207/s15327906mbr3201_3

Cited by 1,206 publications

(1,296 citation statements)

References 0 publications

Supporting

Mentioning

1,264

Contrasting

Unclassified

Order By: Relevance

“…Assured anonymity and confidentiality were implemented to reduce the possibility of social desirability influencing survey responses. covariance structures modeling (MACS; Little 1997). Each sample (previously published and present) has its own representative model reflecting factor structure.…”

Section: Eals Long-form Measurement Invariancementioning

confidence: 99%

Evolutionary Attitudes and Literacy Survey (EALS): Development and Validation of a Short Form

Short

Hawley

2012

Evo Edu Outreach

View full text Add to dashboard Cite

The Evolutionary Attitudes and Literacy Survey (EALS) is a multidimensional scale consisting of 16 lower- and 6 higher-order constructs developed to measure the wide array of factors that influence both an individual’s endorsement of and objection to evolutionary theory. Past research has demonstrated the validity and utility of the EALS (Hawley et al., Evol Educ Outreach 4:117–132, 2011); however, the 104-item long-form scale may be excessive for researchers and educators. The present study sought to reduce the number of items in the EALS while maintaining the validity and structure of the long form. For the present study, and following best practices for short-form construction, we surveyed a new sample of several hundred undergraduates from multiple majors and reduced the long form by 40% while maintaining the scale structure and validity. A multiple-group confirmatory factor analysis supported strong factorial invariance across samples, and therefore verified structure and pattern between the six higher-order constructs of the long-form EALS and the EALS short form (EALS-SF). Regression analysis further demonstrated the short form’s validity (i.e., demographics and openness to experience) and replicated previous findings. In the end, the EALS-SF may be a versatile tool that may be used whole or in part for a variety of research areas, including curricular effectiveness of courses on evolution and/or biology.

show abstract

Section: Eals Long-form Measurement Invariancementioning

confidence: 99%

Evolutionary Attitudes and Literacy Survey (EALS): Development and Validation of a Short Form

Short

Hawley

2012

Evo Edu Outreach

View full text Add to dashboard Cite

show abstract

“…Measurement invariance (MI) analyses are accomplished through specification of a series of increasingly restrictive factor models. Generally speaking, there are four tests of MI (or what Little, 1997, referred to as Category 1 analyses) and two additional tests to assess construct-level invariance (or what Little referred to as Category 2 analyses). Only the Category 1 tests pertain to the question of measurement bias per se.…”

Section: Measurement Biasmentioning

confidence: 99%

An examination of psychometric bias due to retesting on cognitive ability tests in selection settings.

Lievens¹,

Reeve²,

Heggestad³

2007

Journal of Applied Psychology

108

View full text Add to dashboard Cite

Using a latent variable approach, the authors examined whether retesting on a cognitive ability measure resulted in measurement and predictive bias. A sample of 941 candidates completed a cognitive ability test in a high-stakes context. Results of both the within-group between-occasions comparison and the between-groups within-occasion comparison indicated that no measurement bias existed during the initial testing but that retesting induced both measurement and predictive bias. Specifically, the results suggest that the factor underlying the retest scores was less saturated with g and more associated with memory than the latent factor underlying initial test scores and that these changes eliminated the test's criterionrelated validity. This study's implications for retesting theory, practice, and research are discussed.

show abstract

“…The statistical differences and similarities may support partial measurement invariance of some of the constructs in some countries. However, the constrained (metrically invariant) model is substantially more parsimonious and meaningful than the model with only configural invariance, and it is reasonable to accept it (Little 1997). Table 5 about here 10 As the sample size is very large, we do not apply the chi-square difference test (Cheung and Rensvold 2002).…”

mentioning

confidence: 99%

Bringing Values Back In: The Adequacy of the European Social Survey to Measure Values in 20 Countries

Davidov

Schmidt

Schwartz

2008

Public Opinion Quarterly

559

475

View full text Add to dashboard Cite

Values are prominent in public discourse today. Theorists have long considered values central to understanding attitudes and behavior. The Schwartz (1992) theory of basic human values has promoted a revival of empirical research on values. The semi-annual European Social Survey (ESS) includes a new 21-item instrument to measure the importance of the ten basic values of the theory. Representative national samples in 20 countries responded to the instrument in 2002-3. We briefly describe the theory and the ESS instrument and assess its adequacy for measuring values across countries. Using multiple group confirmatory factor analyses, augmented with mean-structure information, we assess the configural and measurement (metric) invariance of the values-necessary conditions for equivalence of the meaning of constructs, and scalar invariance-a precondition for comparing value means across countries. Only if such equivalence is established can researchers make meaningful and clearly interpretable cross-national comparisons of value priorities and their correlates. The ESS values scale demonstrates configural and metric invariance, allowing researchers to use it to study relationships among values, attitudes, behavior and socio-demographic characteristics across countries. Comparing the mean importance of values across countries is possible only for subsets of countries where scalar invariance holds.

show abstract

Mean and Covariance Structures (MACS) Analyses of Cross-Cultural Data: Practical and Theoretical Issues

Cited by 1,206 publications

References 0 publications

Evolutionary Attitudes and Literacy Survey (EALS): Development and Validation of a Short Form

Evolutionary Attitudes and Literacy Survey (EALS): Development and Validation of a Short Form

An examination of psychometric bias due to retesting on cognitive ability tests in selection settings.

Bringing Values Back In: The Adequacy of the European Social Survey to Measure Values in 20 Countries

Contact Info

Product

Resources

About