A Monte Carlo Study of Migration and Child Educational Production: Aggregated vs. Disaggregated Resource Modeling

Posted: 28 Feb 2013

See all articles by Thomas A. Mroz

Thomas A. Mroz

Department of Economics, Andrew Young School of Policy Studies

Guo Li

Fannie Mae

Date Written: February 26, 2013

Abstract

This paper studies the sensitivity of estimates on various assumptions about aggregation in modeling the school's effect in child educational production. Building a structural model to control the endogeneity of school qualities in the production function, the authors uses Monte Carlo simulations to evaluate the performance of a "correct" aggregation educational production model versus simple aggregation educational production model in estimating school resources' effect on academic outcome. Comparion of both specifications to the benchmark model without aggregation shows that the simple aggregation of school resources over a geographic area causes serious specification errors, and thus generate biased estimates for the marginal contribution of the school resources to test scores. Fortunately, such biasedness can be minimized by using the "correct" aggregation specification.

Keywords: Migration, Endogeneity Control, Aggregation, Educational Production Function

JEL Classification: I20, J62

Suggested Citation

Mroz, Thomas A. and Li, Guo, A Monte Carlo Study of Migration and Child Educational Production: Aggregated vs. Disaggregated Resource Modeling (February 26, 2013). Available at SSRN: https://ssrn.com/abstract=2225473 or http://dx.doi.org/10.2139/ssrn.2225473

Thomas A. Mroz

Department of Economics, Andrew Young School of Policy Studies ( email )

P.O. Box 3992
Atlanta, GA 30302-3992
United States

Guo Li (Contact Author)

Fannie Mae ( email )

3900 Wisconsin Ave NW
Washington DC, DC 20003
United States

Register to save articles to
your library

Register

Paper statistics

Abstract Views
276
PlumX Metrics