‘Do better schools matter? Parental valuation of elementary education’
Quarterly Journal of Economics 114, No. 2, pp. 577-599
Uses house prices to infer the value parents place on school quality, using houses on the boundaries of attendance districts to control for unobserved neighbourhood characteristics.
The study uses data from Massachusetts, and focuses entirely on Tiebout type school choice. It therefore only examines districts where public school attendance is determined purely by housing location.
Key results:
A 5% increase in test scores is associated with a 2.1% increase in house prices – worth $3,948 at the mean.
When unobserved heterogeneity is not controlled for (as in many traditional studies) the effect doubles: a 5% increase in average elementary school test score is associated with a 4.9% increase in the house price – equivalent to $9,280 at the mean.
Thus the paper provides stark evidence that inadequate controls based only on observable characteristics will lead to (100%!) overestimates of this valuation.