Construction of a Structural Equation Model on Attitudes to Science Using LISREL

The purpose of this study is to construct a structural equation model and to analyze causal relationships among variables related to to using structural equation modeling(SEM) with LISREL VII. The sample consisted of 483 10th grade boys from a general high school in Pusan, Korea. The questionnaires (ABC-attitude scale: affection, behavioral intention, cognition scale of attitude towards science) were developed by the researcher through a pilot study. And other instruments have modified previous ones. Five instruments were used in this study: GALT(group assessment of logical thinking), MTSlS(modified test of inquiry skill), ABC-attitude scale, MSAS(modified scientific attitude scale), CSAT(common achievement test). Structural equation modeling with LISREL VII( & 1993) was employed to estimate the causal inferences about hypothesized relationships among observed data sets. Three competing models consisted of five latent variable(scientific thinking ability, inquiry skill, attitude towards science, scientific attitude, achievement) - lP(inquiry preceding) model, AP(attitude preceding) model and AM(attitude mediating) model - were developed. Among these competing models, IP model satisfied the observed data sets. The causal relationships among attitudes to science and other latent variables were reliably identified. According to the results of the present study, inquiry skill was the most significant variable that can predict achievement. But scientific thinking ability has not directly influenced achievement. This study suggests that inquiry based teaching-learning processes should be offered to students for improvement of achievement. At the same time, it seems to be important to develop positive attitude towards science. Understanding of relationships among variables related to to will be helpful to the development of curriculum and to the design of teaching and learning process. LISREL has been recognized as a useful approach in testing a SEM. However, in this study, LISREL approach was estimated as much more useful method for research design.