Structural Equation with Lavaan by Gana Kamel; Broc Guillaume; & Guillaume Broc

Author:Gana, Kamel; Broc, Guillaume; & Guillaume Broc [Gana, Kamel & Broc, Guillaume]
Language: eng
Format: epub
Publisher: John Wiley & Sons, Incorporated
Published: 2019-01-07T00:00:00+00:00

Figure 3.12. Higher-order (second-order) CFA model The variances – curved double arrows – of the exogenous latent variables have not been represented

3.5.1.3.1. Illustration

The following illustration has three objectives. First, to demonstrate how to use a correlation matrix accompanied by standard deviations, as the input matrix for lavaan, in the place of the unavailable raw data, to estimate a model. Next, to show how to retranscribe in lavaan syntax, estimating, and then evaluating a higher-order CFA model. Finally, comparing the hierarchical factor solution with a bifactorial solution, which will be presented later.

The correlations matrix and the standard deviations come from a paper by Marsh and Hocevar [MAR 85] in which these authors proposed to test the factorial structure of the Self-Description Questionnaire (SDQ). The SDQ is a multidimensional scale of self-concept. It measures four non-academic aspects of self-concept (physical ability, physical appearance, relations with peers, relations with parents) and three academic aspects of self-concept (reading, mathematics, general school) in children and teenagers. For the purpose of this illustration, we will restrict ourselves here to the four non-academic self-concept dimensions measured among 251 students (grade 5). Each dimension was measured by four indicators (items).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.