Email this article The finite iterative method for calculating the correlation matrix implied by a recursive path model
Abstract
The computation of the implied correlation matrix using a recursive structural equation model without latent variables "Path Analysis" is a crucial step. This can be made by the said Jöreskog' method which requires matrix inversion. This paper presents an alternative method of calculation. The originality of this new method is that it is based on direct calculations for obtaining the explicit expression of the implied correlation matrix in terms of model parameters whatever the complexity of the model.
References
Boudon, R. (1965). Méthodes d'analyse causale. Revue française de sociologie. Vol. 6, No. 1 (Jan. - Mar., 1965), pp. 24-43
Duncan, O. D. (1966). Path analysis: Sociological examples. American Journal of Sociology, 72, 1-16.
Heise, D. R. (1969). Problems in path analysis and causal inference. pp. 38-73 in E. F. Borgatta (ed.) Sociological Methodology. San Francisco. Jossey-Bass.
Hauser, R. M & Sewall, W. H. (1975). Education, occupation, and earnings. New York: Academic Press.
Wright, S. (1921). Correlation and causation. Journal of Agricultural Research 20, 557–585. 17
Jöreskog, K.G. (1977). Structural Equation Models in the Social Sciences: Specification, Estimation and Testing. In: Applications of Statistics, 265-287. R. Krishnaiah (Ed). Amsterdam: North-Holland.
Jöreskog, K.G and Wold, H. (1982), Systems under indirect observation: Causality, structure, prediction, Part I and Part II. Amsterdam: North Holland.
Hoyle, R. H. (2000). Confirmatory Factor Analysis. In: Handbook of Applied Multivariate Statistics and Mathematical Modeling, 465-497. H.E.A. Tinsley and S. D. Brown (Eds). New York: Academic Press.
Full Text: pdf
