Improving the Interpretability of the Variances of Latent Variables by Uniform and Factor-Specific Standardizations of Loadings
Abstract
The variances of latent variables are presented as statistics that support the evaluation of a model in confirmatory factor analysis. Appropriate standardization even improves the benefit of investigating variances. The variances integrate the information concerning the individual loadings and are associated with an error probability. The estimation of the variances of latent variables requires the estimation of the loadings in the first step and their replacement by constraints according to the estimates in the second step. Uniform or factor-specific standardization is necessary for achieving comparability of the variances. The usefulness of standardization is demonstrated in models from optimism research. Three ways of standardization were considered: uniform standardization, factor-specific standardization, and standardization by setting one loading equal to one. Generally valid results were achieved by uniform standardization. If some loadings were set equal to zero, factor-specific standardization even yielded better results. The results of the remaining way were very specific.
References
1987). Factor analysis and AIC. Psychometika, 52, 317–322.
(2007). Structural equation modeling: Adjusting model fit. Personality and Individual Differences, 42, 815–824.
(1989). Structural equations with latent variables. New York: Wiley.
(2006). Confirmatory factor analysis. New York, NJ: The Guilford Press.
(2006). Evaluating latent curve models using individual fit statistics. Structural Equation Modeling, 13, 1–27.
(1995). Modeling the processes of development via latent variable growth curve methodology. Structural Equation Modeling, 2, 187–213.
(2004). An introduction to latent growth curve modeling. Behavior Therapy, 35, 333–363.
(1970). A general method for analysis of covariance structure. Biometrika, 57, 239–257.
(1971). Statistical analysis of sets of congeneric tests. Psychometrika, 36, 109–133.
(2001). LISREL 8: User’s reference guide. Chicago, IL: Scientific Software International.
(2005). Goodness of fit in structural equation models. In , Contemporary psychometrics: A festschrift for Roderick P. McDonald (pp. 275–340). Mahwah, NJ: Erlbaum.
(1986). Latent variable growth within behavior genetic models. Behavior Genetics, 16, 163–200.
(1988). Growth curve analysis in contemporary psychological research. In , Handbook of multivariate experimental psychology (2nd ed., pp. 561–614). New York: Plenum.
(1987). Latent growth curves within developmental structural equation models. Child Development, 58, 110–133.
(1984). Tuckerizing curves. Paper presented at the annual meeting of the Psychometric Society. Santa Barbara, CA.
(1990). Latent curve analysis. Psychometrika, 55, 107–122.
(1958). Some statistical methods for comparisons of growth curves. Biometrics, 14, 1–17.
(2007). Method effects due to social desirability as a parsimonious explanation of the deviation from unidimensionality in LOT-R scores. Personality and Individual Differences, 42, 1597–1607.
(2003). Testing equality of proportions explained latent variance in structural equation modelling. Structural Equation Modeling, 10, 534–543.
(1994). Distinguishing optimism from neuroticism (and trait anxiety, self-mastery, and self-esteem): A re-evaluation of the Life Orientation Test. Journal of Personality & Social Psychology, 67, 1063–1078.
(1960). Factor analysis of the electrocardiograph. Circulation Research, 8, 519–526.
(2006a). The fixed-links model in combination with the polynomial function as tool for investigating choice reaction time data. Structural Equation Modeling, 13, 403–419.
(2006b). The fixed-links model for investigating the effects of general and specific sources. Methodology: European Journal of Research Methods for the Behavioral and Social Sciences, 2, 149–160.
(2007). Investigating the relationship of working memory tasks and fluid intelligence tests by means of the fixed-links model in considering the impurity problem. Intelligence, 35, 591–604.
(2008). Investigating experimental effects within the framework of structural equation modeling: An example with effects on both error scores and reaction times. Structural Equation Modeling, 15, 327–345.
(2009). Fixed-links models for investigating experimental effects combined with processing strategies in repeated measures designs: A cognitive task as example. British Journal of Mathematical and Statistical Psychology, 62, 217–232.
(2008). An investigation of the structure of the social optimism scale in considering the dimensionality problem. Journal of Individual Differences, 29, 223–230.
(2001). Personaler und Sozialer Optimismus.
(Personal and social optimism Zeitschrift für Differentielle und Diagnostische Psychologie, 22, 13–24.1958). Determination of parameters of a functional relation by factor analysis. Psychometrika, 23, 19–23.
(2004). A bistable view of single constructs measured using balanced questionnaires: Application to trait anxiety. Structural Equation Modeling, 11, 261–271.
(2003). Dimensionality of the Revised Life Orientation Test and the status of filler items. International Journal of Psychology, 38, 390–400.
(2005). Imperfect or perfect dynamic bipolarity? The case of antonymous affective judgements. Structural Equation Modeling, 12, 391–410.
(