This paper provides an overview of the quantitative features of research design adopted in the Department for Children, Schools and Families (DCSF; formerly DfES) funded, longitudinal mixed method study intended to investigate the impact of school leadership on pupil outcomes. It outlines the way quantitative analyses of national assessment and examination datasets have been used to identify a sample of highly effective and improving schools for further investigation. Some examples of the findings from the interim analyses of survey responses by headteachers and key staff are highlighted in relation to patterns of leadership practices of the improvement group of the school. The categorisation of schools into three distinctive improvement and effectiveness groups reveals statistically and educationally significant differences in certain features and practices. There are important relationships between school context and the school improvement group, and between school context and headteachers' time in post.