CORRECTING FOR SAMPLING BIAS IN EDUCATION PRODUCTION FUNCTIONS

Sample selectivity bias arises in the estimation of education production functions when the process of selecting the sample is not independent of the value of the dependent variable. In this study, the dependent variable was a student's retention of microeconomics knowledge after a period of 6 weeks following the final examination. Potential sampling bias arises from a student's decision to participate or not to participate in the research. Results obtained from the Heckman selection model indicated minor sampling bias. Student ability and the male dominance in economics performance were overestimated in the OLS model. Student effort was underestimated.     

THE EFFECT OF STUDENT CHARACTERISTICS ON ACHIEVEMENT IN INTRODUCTORY MICROECONOMICS IN SOUTH AFRICA

This paper uses OLS regression analysis to examine the effect of student characteristics on performance in Introductory Microeconomics at five South African universities. No consistent race‐effects were found, but Indian students performed significantly worse than Whites at historically‐White universities. Male students outperformed females in general. Older students did better at the historically‐White institutions only. At one university, Black students who speak English as their home language outperformed those who are non‐English speakers. Students who devoted more time to study outside formal classes did better in general. Greater verbal and mathematical ability had large and significant positive effects on student achievement.