/ose-data-science-course-project-baharcos

Final Project for Microeconometrics, Summer 2021 | Replication of Angrist et al. (2009) | Bahar Coskun

Primary LanguageJupyter NotebookMIT LicenseMIT

OSE data science student project: Replication of Angrist et al. (2009)

This repository contains my replication of the results of

Angrist et al. (2009). “Incentives and Services For College Achievement: Evidence From A Randomized Trial". American Economic Journal: Applied Economics, 1:1, 136–63.

For optimal results I recommend to clone the repository to your local machine and run the notebook on student_project environment. In order to do so our local machine ideally needs to have Anaconda Navigator. The following badges allow easy access to the project's notebook

Project overview

Angrist et al. (2009) studies the effect of academic services and financial incentives on not so spectacular students in a randomised trial. As the randomisation is diluted for participation, they employ instrumental variables to estimate the causal effect of the program. They argue for a lasting improvement in academic performance of females due to improved stud habits when services and incentives are combined. I replicate the Table 5, Table 8 and Figure 1 from the paper. In extension, I focus on background variables, visualisation for better understanding and gender participation differences.

Continuous Integration and Reproducibility

Continuous Integration

References

Angrist, J., Land, D., & Oreopoulos, P. (2009). Incentives And Services For College Achievement: Evidence From A Randomized Trial. American Economic Journal: Applied Economics, 1(1), 136-63.

Angrist, J. D. and Pischke, J.-S. (2009). Mostly Harmless Econometrics: An Empiricist’s Companion. Princeton University Press (link)

covid-19-impact-lab (link)

Eisenhauer, P. (2021). Project template, OpenSourceEconomics. (link)

Gehlen, A. (2019). Replication of Jason M. Lindo, Nicholas J. Sanders & Philip Oreopoulos (2010). (link)