This paper is concerned with the relationship between class size and the student outcome - participation in post-compulsory schooling. Our analysis applies a regression discontinuity design based on administrative rules for school inputs during compulsory schooling to uncover the effect on post-compulsory schooling. Research on this topic has been problematic partly because omitted unobservables are likely to be correlated with class size. Two potential ways to resolve this are to exploit experimental or instrumental variation. In both cases, the methods require that variation should not be contaminated by other unobservable factors that affect the outcome. An alternative approach is to take advantage of variation in class size between siblings. The distinctive aspect of this study is that we contrast results which attempts to exploit natural experimental variation in class size with results that control for family, neighbourhood and school effects by way of sibling differences. Our aim is to examine the robustness of estimates of the effects of class size in the context of length of education.

Download full version (PDF 474 KB)