This document analyzes the impact of homework on student achievement. It utilizes both parametric and nonparametric techniques on data from the National Educational Longitudinal Study of 1988. The results indicate:
1) Homework has a larger and more significant impact on test scores than other standard school inputs like class size.
2) The effects of homework are not uniform - it is most effective for high- and low-achieving students.
3) Parametric models overstate the impact of school inputs like homework and class size compared to nonparametric estimates.