Hierarchical Network Item Response Modeling for Discovering Differences Between Innovation and Regular School Systems in Korea
The innovation school system has been implemented in Korea to cultivate a bottom-up education culture in public education. The effectiveness of the program, however, has been under close scrutiny as numerous studies reported mixed results about its effects on students' non-cognitive outcomes. We proposed and applied a novel analytic technique, hierarchical network item response modeling to multilevel item response data, in order to examine and discover subtle and in-depth differences between innovation and regular school programs in terms of items and school network structures. Our analysis found minimal evidence that the students in the innovation schools showed higher levels of desirable attributes, such as the sense of citizenship, democracy, and autonomy, compared with students in regular schools.
READ FULL TEXT