Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation
A growing number of school districts use centralized assignment mechanisms to allocate school seats in a manner that reflects student preferences and school priorities. Many of these assignment schemes use lotteries to ration seats when schools are oversubscribed. The resulting random assignment ope...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
The Econometric Society
2018
|
| Online Access: | http://hdl.handle.net/1721.1/113677 https://orcid.org/0000-0001-6992-8956 https://orcid.org/0000-0002-0772-9457 https://orcid.org/0000-0001-8621-3864 |
| _version_ | 1811083989676457984 |
|---|---|
| author | Abdulkadiroğlu, Atila Angrist, Joshua Narita, Yusuke Pathak, Parag |
| author2 | Massachusetts Institute of Technology. Department of Economics |
| author_facet | Massachusetts Institute of Technology. Department of Economics Abdulkadiroğlu, Atila Angrist, Joshua Narita, Yusuke Pathak, Parag |
| author_sort | Abdulkadiroğlu, Atila |
| collection | MIT |
| description | A growing number of school districts use centralized assignment mechanisms to allocate school seats in a manner that reflects student preferences and school priorities. Many of these assignment schemes use lotteries to ration seats when schools are oversubscribed. The resulting random assignment opens the door to credible quasi-experimental research designs for the evaluation of school effectiveness. Yet the question of how best to separate the lottery-generated randomization integral to such designs from non-random preferences and priorities remains open. This paper develops easily-implemented empirical strategies that fully exploit the random assignment embedded in a wide class of mechanisms, while also revealing why seats are randomized at one school but not another. We use these methods to evaluate charter schools in Denver, one of a growing number of districts that combine charter and traditional public schools in a unified assignment system. The resulting estimates show large achievement gains from charter school attendance. Our approach generates efficiency gains over ad hoc methods, such as those that focus on schools ranked first, while also identifying a more representative average causal effect. We also show how to use centralized assignment mechanisms to identify causal effects in models with multiple school sectors. |
| first_indexed | 2024-09-23T12:42:50Z |
| format | Article |
| id | mit-1721.1/113677 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T12:42:50Z |
| publishDate | 2018 |
| publisher | The Econometric Society |
| record_format | dspace |
| spelling | mit-1721.1/1136772024-06-28T14:35:56Z Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation Abdulkadiroğlu, Atila Angrist, Joshua Narita, Yusuke Pathak, Parag Massachusetts Institute of Technology. Department of Economics Angrist, Joshua Narita, Yusuke Pathak, Parag A growing number of school districts use centralized assignment mechanisms to allocate school seats in a manner that reflects student preferences and school priorities. Many of these assignment schemes use lotteries to ration seats when schools are oversubscribed. The resulting random assignment opens the door to credible quasi-experimental research designs for the evaluation of school effectiveness. Yet the question of how best to separate the lottery-generated randomization integral to such designs from non-random preferences and priorities remains open. This paper develops easily-implemented empirical strategies that fully exploit the random assignment embedded in a wide class of mechanisms, while also revealing why seats are randomized at one school but not another. We use these methods to evaluate charter schools in Denver, one of a growing number of districts that combine charter and traditional public schools in a unified assignment system. The resulting estimates show large achievement gains from charter school attendance. Our approach generates efficiency gains over ad hoc methods, such as those that focus on schools ranked first, while also identifying a more representative average causal effect. We also show how to use centralized assignment mechanisms to identify causal effects in models with multiple school sectors. 2018-02-15T13:54:38Z 2018-02-15T13:54:38Z 2017-09 2018-02-14T18:31:21Z Article http://purl.org/eprint/type/JournalArticle 0012-9682 1468-0262 http://hdl.handle.net/1721.1/113677 Abdulkadiroğlu, Atila et al. “Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation.” Econometrica 85, 5 (2017): 1373–1432 © 2017 The Econometric Society https://orcid.org/0000-0001-6992-8956 https://orcid.org/0000-0002-0772-9457 https://orcid.org/0000-0001-8621-3864 http://dx.doi.org/10.3982/ECTA13925 Econometrica Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf The Econometric Society SSRN |
| spellingShingle | Abdulkadiroğlu, Atila Angrist, Joshua Narita, Yusuke Pathak, Parag Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation |
| title | Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation |
| title_full | Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation |
| title_fullStr | Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation |
| title_full_unstemmed | Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation |
| title_short | Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation |
| title_sort | research design meets market design using centralized assignment for impact evaluation |
| url | http://hdl.handle.net/1721.1/113677 https://orcid.org/0000-0001-6992-8956 https://orcid.org/0000-0002-0772-9457 https://orcid.org/0000-0001-8621-3864 |
| work_keys_str_mv | AT abdulkadirogluatila researchdesignmeetsmarketdesignusingcentralizedassignmentforimpactevaluation AT angristjoshua researchdesignmeetsmarketdesignusingcentralizedassignmentforimpactevaluation AT naritayusuke researchdesignmeetsmarketdesignusingcentralizedassignmentforimpactevaluation AT pathakparag researchdesignmeetsmarketdesignusingcentralizedassignmentforimpactevaluation |