Using Data Mining to Explore Factors That Distinguish Between Students With High and Low Mathematical Literacy Performance — An Example With Socio-Economically Disadvantaged and Advantaged Students in Macao

Using Macao-PISA 2012 data collected from socio-economically disadvantaged and advantaged students, this study identified two sets of important learning factors that distinguished between low- and high-performing disadvantaged students, and between low- and high-performing advantaged students, respectively. The findings of this research contribute to a better understanding of the reasons for Macao’s high-quality and equitable education as compared to other regions with high mathematical literacy performance while also revealing the crux of small inequities in its education system. The analysis method used in this paper provides a paradigm for data mining research using large-scale assessment data and helps researchers better grasp the state of education at the local level.