Documentation for “Revisiting The Impact Of Teachers,” by Jesse Rothstein
I. Current version
The most recent version of the paper, dated January 2017, is available here.
II. Version prepared for publication
A version of the paper is forthcoming in the American Economic Review. This version is here. The text of the paper is essentially identical to the working paper version above. However, the AER version excludes some supplementary material that is in Appendix B and C of the above working paper.
III. Policy brief
A policy brief summarizing the key results of the paper is here.
IV. The exchange
The paper is part of an extended exchange. It responds to two papers:
- Chetty, Raj, John N. Friedman, and Jonah E. Rockoff, “Measuring the Impact of Teachers I: Evaluating Bias in Teacher Value-Added Estimates,” American Economic Review 104, p. 2593-2632.
- Chetty, Raj, John N. Friedman, and Jonah E. Rockoff, “Measuring the Impact of Teachers II: Teacher Value-Added and Student Outcomes in Adulthood,” American Economic Review 104, p. 2633-2679.
Chetty et al. have responded several times to earlier versions of the paper (linked below). The most recent responses include:
- Chetty, Raj, John N. Friedman, and Jonah E. Rockoff, “Measuring the Impact of Teachers: Response to Rothstein (2014),” CEPR Discussion paper 10768, August 2015.
- Chetty, Raj, John N. Friedman, and Jonah E. Rockoff, “Using Lagged Outcomes to Evaluate Bias in Value-Added Models,” NBER Working Paper 21961, February 2016.
- Chetty, Raj, John N. Friedman, and Jonah E. Rockoff, “Measuring the Impact of Teachers: Response to Rothstein (2016),” December 2016. Forthcoming, American Economic Review.
Another paper responding to the Rothstein comment is:
Appendix C of the working paper above responds to the critiques from Chetty, Friedman, and Rockoff. This response is also available as a stand-alone paper:
V. Older versions
Three earlier versions of the Rothstein paper circulated as working papers. These are dated October 2014, October 2015, and March 2016. Click on the above dates to access these papers.
For completeness, I also include here the initial version of my rejoinder to Chetty et al.’s Reply, dated March 2016.
VI. Data and replication
The Rothstein work relies on restricted-use data obtained under license from the North Carolina Education Research Data Center. Because these data are confidential, they cannot be distributed. Interested researchers are encouraged to contact the NCERDC at the above link to request access.
I have prepared a replication archive of programs used to conduct my analysis, here. This is accompanied by:
- A readme file, describing the contents of the program archive and providing replication instructions.
- A manifest, listing all included files.
- A guide to program structure that indicates dependencies, execution order, and the base data on which each program relies.
- A list of all project files, including raw data, programs, logs, and constructed data, with checksums for each file.
Please contact me if you have any questions about the replication files.
