The effect of gender on learner achievement in Gauteng and the Western Cape Provinces of South Africa

Abstract

Fixed effects models, which assume that all observations are independent of each other, are not appropriate for analysis of correlated data. To ensure that every learner achieves high academic standards, it is important to understand aggregate data. However, it is even more important to understand the disaggregated data. The aggregated analysis’ result shows that the difference of the overall performances (49.377 and 50.099) favoured the learners from the Western Cape Province than Gauteng Province. The crude estimates indicate that the learners from the Western Cape Province than those from Gauteng Province are 1.161126 (95% Confidence Interval = 1.131252 - 1.191788) more likely to pass Grade 12. Similarly, the gender adjusted model indicates that the learners from the Western Cape Province than those from Gauteng Province are significantly 1.161375 (95% Confidence Interval = 1.131487 - 1.192053) more likely to pass Grade 12. The effect of gender favoured the Western Cape Province.

Keywords: Clustered data; aggregated analysis; hierarchical linearmodels; performance; learner gender