Methodology: Cluster Analysis of Motivation Variables in the TIMSS Data

Abstract

This chapter begins with a description of the IEA’s Trends in International Mathematics and Science Study (TIMSS) sampling framework. The research study was based on data from three cycles of TIMSS collected at grades four and eight from 12 jurisdictions (Australia, England, Hong Kong, Hungary, Iran, Japan, Norway, Ontario, Quebec, Singapore, Slovenia, and the USA) that participated at both grades in 1995, 2007, and 2015. The motivation variables available in each cycle of administration are outlined, together with how conceptually similar measures for value, enjoyment, and self-confidence in mathematics were constructed; descriptions of demographic and achievement measures used in the analysis are also provided. Two-step cluster analysis was used to create separate profiles of student motivation for each set of data. The characteristics of each motivational cluster were evaluated to ascertain whether differences in cluster membership were related to student background variables (such as sex, time on homework, parental education, and home resources) and mathematics achievement.