Average Does Not Fit All: The Effects of Student Characteristics on Predicting Self-Efficacy

• In Event: Marriott Roundtable Session 2
  In Roundtable Session: Comparative Studies in Mathematics Education

Abstract

This study applied quantile regression (QR) to the examination of individual differences in mathematics self-efficacy, using the 2003 and 2012 Programme for International Student Assessment data. The QR results showed that the effects of many student characteristics were not constant across the mathematics self-efficacy distributions. Standardized coefficients were used to discuss whether mathematics self-efficacy were stable across time. Location, scale and shape shifts were compared across quantiles between 2003 and 2012 to see the different effects of the demographic variables. QR improves empirical research by dividing the sample into different student quantiles that show the effect of each independent variable for specific quantiles of students. This allows for the comparison of independent variables on students at different mathematics self-efficacy quantiles.

Authors

• Jing Yuan, Guilin Christian Church

• Xin Ma, University of Kentucky