Interpreting Instrumental Variables Estimates of the Returns to Schooling

Author
Keywords
Abstract

An instrumental variable can be used to identify the labor market return to schooling by
allowing comparisons between groups of individuals whose differences in schooling levels are
uncorrelated with their underlying marginal benefit from schooling and with other aspects of
unobserved ability. When the education decisions are based on individual-specific marginal
beneļ¬ts and costs, there is no single rate of return for everyone in the population. This paper
demonstrates economic insights from methods interpreting instrumental variables estimates as
weighted averages of individual-specific causal effects of schooling on wages by synthesizing
existing theoretical and econometric work, and by using geographic variation in college
proximity as an example of an instrumental variable.
Characterizing the groups affected by the college proximity instrument, I find the largest
increase in schooling levels among individuals from more disadvantaged backgrounds.
Although the data is insufficient to obtain useful estimates of group-specific rates of return, I
directly compute the weight each group receives in the overall estimate. In analyzing the
response function and showing the level of schooling at which individuals change their behavior
in response to the instrument, I demonstrate that the instrument has the greatest impact on the
transition from high school to college. This corresponds to the economic intuition that changes
in the marginal cost of college should be concentrated at this transition and should not affect all
levels of schooling equally. The results suggest that disadvantaged groups are most responsive
to policies lowering college costs, and that increases in education for these groups may have high
payoff.

Year of Publication
1999
Number
415
Date Published
01/1999
Publication Language
eng
Citation Key
Journal of Business and Economic Statistics, Volume 19, No. 3, July 2001
URL
Working Papers