Determination of the Characteristics Predicting Science Achievement through the Classification and Regression Tree (CART) Method: The Case of TIMSS 2015 Turkey

In the current study, it was aimed to determine student, teacher and school characteristics that predict science achievement of eight grade students in Turkey. data TIMMS 2015 were used study group comprised a total 6079 220 teachers from 218 different schools. As collection tools, eighth test scales administered reflecting used. Since there multi-level structure where nested schools, created model analyzed by using RE-EM algorithm, which enables structures be through classification regression tree (CART) method. The predicted variable students’ scores predictor variables seventeen expressed scales. According results obtained, determined five achievement, are confident science, student bullying, teaching limited needs, discipline problems emphasis on academic success. It has been observed who have confidence level bullying they exposed to, success their schools more, whose stated more successful.