Estimating Scottish student retention rates using propensity score matching

The performance of institutions such as universities and colleges is of increasing interest to funders, policy makers, potential students and the establishments themselves who require accurate estimates of outcomes such as retention rates across the different institutions. The UK government has an aim of reducing the cost of non-completion by students, the institutions themselves are concerned with retaining student numbers because they affect reputation and financial health, and prospective students must choose which institution they would prefer to attend. This study controls for differences in student background characteristics in a comparison of retention of Scottish students in Scottish Higher Education Institutions (HEIs) with Scottish students studying at HEIs elsewhere in the UK. The latter group is known to have better retention than the former. Propensity score matching is applied to the Scottish cohort of students, as a preliminary to producing an imputation of their counterfactual outcome. The findings show that Scottish students would be approximately 2 percentage points less likely to continue their studies if they had studied in Scotland rather than studied elsewhere in the UK