Analysis of 2006 PISA Science Performance via Multilevel Statistical Methods

Tülin Acar, Tuncay Öğretmen

Abstract

The aim of this research is to check on the performances Turkish students as displayed in 2006-PISA sciences test according to their student and school levels and whether there are any similarities between the results of HLM and Mplus software prepared for multilevel analysis methods. As the common results of two programs have been evaluated regarding whether 2006- PISA Sciences test performances of Turkish students differ according to student and school levels, data obtained from multilevel analysis programs shows that all variables at the school level influenced 2006-PISA Sciences performances of students. Whether or not there is any similarity between the results of HLM and Mplus programs which are prepared for multilevel analysis methods has been examined and it was found that both programs produce similar results.

Keywords

Hierarchical linear modeling, multilevel models, PISA-2006 science achievement

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.