Abstract
Abstract. Theoretical researchers consider Structural Equation Modeling (SEM) to be the preferred method to study the relationships among latent variables. However, SEM has the disadvantage of requiring a large sample size, especially if the model is complex. Furthermore, since SEM estimates all parameters simultaneously, one misspecification in the model may influence the whole model. For these reasons, applied researchers often use a two-step Factor Score Regression (FSR) approach. In the first step, factor scores are calculated for the latent variables, which are used to perform a linear regression in the second step. However, this method results in incorrect regression coefficients. Croon (2002) developed a method that corrects for this bias. We combine this method of Croon (2002) with path analysis, resulting in Factor Score Path Analysis. This method results in correct path coefficients and has some advantages over SEM: it requires smaller sample sizes, can handle more complex models and the method is less sensitive to misspecifications, because of its stepwise nature. In conclusion, this method can be a suitable alternative for SEM, when one is dealing with a complex model and small sample sizes.
References
(1937). The statistical conception of mental factors. British Journal of Psychology. General Section, 28, 97–104. doi: 10.1111/j.2044-8295.1937.tb00863.x
(1996). An alternative two stage least squares (2SLS) estimator for latent variable equations. Psychometrika, 61, 109–121. doi: 10.1007/BF02296961
(2002).
Using predicted latent scores in general latent structure models . In G. MarcoulidesI. MoustakiEds., Latent variable and latent structure modeling (pp. 195–223). Mahwah, NJ: Erlbaum.(2016). Hypothesis testing using factor score regression: A comparison of four methods. Educational and Psychological Measurement, 76, 741–770. doi: 10.1177/0013164415607618
(2006). Measurement model quality, sample size, and solution propriety in confirmatory factor models. Multivariate Behavioral Research, 41, 55–64. doi: 10.1207/s15327906mbr4101
(2013).
Bias in factor score regression and a simple solution . In A. R. de LeonK. C. ChoughEds., Analysis of mixed data: Methods & applications (pp. 43–61). Boca Raton, FL: Chapman & Hall. doi: 10.1201/b14571-5(2015). Principles and practice of structural equation modeling (4th ed.). New York, NY: Guilford.
(2011). Two new methods for estimating structural equation models: An illustration and a comparison with two established methods. International Journal of Research in Marketing, 28, 258–268. doi: 10.1016/j.ijresmar.2011.03.006
. (2016). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from https://www.r-project.org/
(2012). lavaan: An R package for structural equation modeling. Journal of Statistical Software, 48, 1–36. doi: 10.18637/jss.v048.i02
(1996). A beginner’s guide to structural equation modeling. Mahwah, NJ: Erlbaum.
(2001). Regression among factor scores. Psychometrika, 66, 563–575. doi: 10.1007/BF02296196
(1934). The meaning of i in the estimate of g. British Journal of Psychology, 25, 92–99. doi: 10.1111/j.2044-8295.1934.tb00728.x
(1938). Methods of estimating mental factors. Nature, 141, 246. doi: 10.1038/141246a0
(1935). The vectors of mind. Chicago, IL: University of Chicago Press.
(2003). Indications and limitations of structural equation modeling in complex surveys: Implications for an application in the Medical Expenditure Panel Survey (MEPS). 2003 JSM Proceedings of the American Statistical Associations: Section on survey research methods indications (pp. 4345–4352). San Francisco, CA.
