This paper provides a general formulation of the regression discontinuity (RD) design and shows its general applicability to many epidemiological problems. It then applies the RD method to estimate the e�ects of the 1995 pill scare in the UK, using individual birth records and aggregate...

This paper examines the impacts of family inputs - i.e., maternal employment, child care and home learning - on the early development of British children. Using rich longitudinal data from the UK Millennium Cohort Study we estimate cognitive and non-cognitive achievement production functions...

Using large longitudinal survey data from the UK Millennium Cohort Study, this paper estimates the effec of maternal time inputs on early child development. We find that maternal time is a quantitatively important determinant of skill formation and that its effect declines with child age. There...