Posted Content•
The causal effect of education on earnings
TL;DR: This paper surveys the recent literature on the causal relationship between education and earnings and concludes that the average (or average marginal) return to education is not much below the estimate that emerges from a standard human capital earnings function fit by OLS.
Abstract: This paper surveys the recent literature on the causal relationship between education and earnings. I focus on four areas of work: theoretical and econometric advances in modelling the causal effect of education in the presence of heterogeneous returns to schooling; recent studies that use institutional aspects of the education system to form instrumental variables estimates of the return to schooling; recent studies of the earnings and schooling of twins; and recent attempts to explicitly model sources of heterogeneity in the returns to education. Consistent with earlier surveys of the literature, I conclude that the average (or average marginal) return to education is not much below the estimate that emerges from a standard human capital earnings function fit by OLS. Evidence from the latest studies of identical twins suggests a small upward "ability" bias -- on the order of 10%. A consistent finding among studies using instrumental variables based on institutional changes in the education system is that the estimated returns to schooling are 20-40% above the corresponding OLS estimates. Part of the explanation for this finding may be that marginal returns to schooling for certain subgroups -- particularly relatively disadvantaged groups with low education outcomes -- are higher than the average marginal returns to education in the population as a whole.
Citations
More filters
TL;DR: In this paper, the authors estimate returns to schooling for young men and women in Turkey using the exogenous and substantial variation in schooling across birth cohorts brought about by the 1997 reform of compulsory schooling within a fuzzy regression discontinuity design.
Abstract: In this paper, we estimate returns to schooling for young men and women in Turkey using the exogenous and substantial variation in schooling across birth cohorts brought about by the 1997 reform of compulsory schooling within a fuzzy regression discontinuity design. We estimate that the return from an extra year of schooling is about 7–8% for women and an imprecisely estimated 2–2.5% for men. The low level of the estimates for men contrasts starkly with those estimated for other developing countries. We identify several reasons why returns to schooling are low for men and why they are higher for women in our context. In particular, the policy alters the schooling distributions of men and women differently, thus the average causal effect puts a higher weight on the causal effect of schooling at higher grade levels for women than for men.
39 citations
TL;DR: In this article, the authors show that there is an important correlation between local human capital and average wages after controlling for individual characteristics, and that the estimated social returns to education range from 2 to 3%, whereas the private returns amount roughly to 6-7%.
Abstract: The paper estimates social returns to education in the Italian local labor markets. It shows that there is an important correlation between local human capital and average wages after controlling for individual characteristics. Estimated social returns to education range from 2 to 3%, whereas the private returns amount roughly to 6–7%. To find some support about causality running from local human capital to wages, the paper performs a number of robustness checks. It shows that: the estimated social returns are unlikely to be driven by spatially correlated omitted variables; they survive to the introduction of individual- and territorial-level variables; they are not due to imperfect substitutability across workers or spatial sorting; they are robust to IV techniques that deal with both local human capital and individual human capital endogeneity.
39 citations
TL;DR: This article used conditional second moments to estimate the return to education in a sample drawn from the National Longitudinal Survey of Youth 1979, and found that using conditional second moment estimates increased the estimate of the return in education from 6.8 to 11.2%.
Abstract: An innovation which bypasses the need for instruments when estimating endogenous treatment effects is identification via conditional second moments. The most general of these approaches is Klein and Vella (J Econom 154:154–164, 2010), which models the conditional variances semiparametrically. While this is attractive, as identification is not reliant on parametric assumptions for variances, the nonparametric aspect of the estimation may discourage practitioners from its use. This paper outlines how the estimator can be implemented parametrically. The use of parametric assumptions is accompanied by a large reduction in computational and programming demands. We illustrate the approach by estimating the return to education using a sample drawn from the National Longitudinal Survey of Youth 1979. Accounting for endogeneity increases the estimate of the return to education from 6.8 to 11.2%.
39 citations
TL;DR: This paper found that college nonattendance decreased substantially between cohorts for both men and women and that these declines were larger for higher-ability students on the 2-year/4-year margin.
Abstract: We characterize changes over time in the choices high school graduates make concerning 2-year attendance, 4-year attendance, and college nonattendance across the joint income and ability distribution. We find that college nonattendance decreased substantially between cohorts for both men and women and that these declines were larger for higher-ability students. On the 2-year/4-year margin, there is evidence of growing ability constraints among women. Furthermore, income has become more important among higher-ability men, and increases in 2-year attendance among high-ability but low-income men come at the expense of 4-year college enrollment. State-level college costs explain little of the changes we document.
39 citations
TL;DR: In this paper, the spatial correlation between shelf space and the error term resulting from store-, consumer-and competitor characteristics is incorporated to obtain valid estimates of shelf space elasticities for allocation decisions.
Abstract: A retailer may allocate shelf space to brands based on factors, unobservable to researchers, which also determine sales. As a consequence, both sales and shelf space are endogenous in historical data, and this leads to inconsistent estimates of shelf space elasticities based on OLS. To obtain valid estimates of shelf space elasticities for allocation decisions, we propose an approach that incorporates the spatial correlation between shelf space and the error term resulting from store-, consumer- and competitor characteristics. The empirical results suggest that our model based on a single cross section of stores corrects for endogeneity and provides valid shelf space elasticities. We also obtain superior predictions compared to several benchmark models. With the same cross section and two observations over time, the alternative methods we use provide comparable shelf space elasticity estimates. However, our proposed method is still superior in the sense that its estimates have somewhat smaller standard errors.
39 citations