Application of Structural Equation Modeling in EFL Testing: A Report of Two Iranian Studies

Abstract

Structural equation modeling (SEM) is a statistical method used for testing and estimating causal relations using a combination of statistical data and qualitative causal assumptions. This paper reports two studies done by the researchers through the application of SEM. In the first study the relationship between EFL learners' affective constructs and their English achievement was assessed using SEM. Since both Structural coefficient and Goodness of fit are high, we conclude that not only is the model accepted but also the relationship between EFL learners' affective constructs and their English achievement is statistically significant. The second study investigated the relationship between Affective constructs and Study Process of EFL learners through the application of SEM. In this study the Goodness of Fit Index (GFI) turned out to be 0.99. Again like the previous study, since the Goodness of Fit Index (GFI) and structural coefficient are high, we conclude that there is a statistically strong relationship between affective constructs and study process of EFL learners.