| Title | Regression Discontinuity Design Meets Market Design: School Effectiveness in Chicago and NYC |
|---|---|
| Date | 2018年12月11日（火）December 11, 2018, 10:25-12:10 |
| Venue | 東京大学経済学研究科・学術交流棟（小島ホール）１階・第１セミナー室にて開催 [地図] Seminar Room No. 1, Economics Research Annex (Kojima Hall), University of Tokyo [MAP] |
| Speaker | 成田悠輔（Yusuke Narita, Yale University and CREPE) |
| Abstract | Centralized school assignment algorithms employ non-lottery tie-breakers like test scores, randomly assigned lottery numbers, or both. The New York City public high school match illustrates the latter, using test scores, grades, and interviews to rank applicants to screened schools, combined with lottery tie-breaking at unscreened schools. We show how to identify causal effects of school attendance in such settings. Our approach generalizes regression discontinuity designs to allow for multiple treatments and multiple running variables, some of which are randomly assigned. Lotteries generate assignment risk at screened as well as unscreened schools. These results are used to assess the predictive value of New York City’s school report cards. Grade A schools improve SAT math scores and increase the likelihood of graduating, though by less than OLS estimates suggest. Grade A attendance also boosts measures of college and career readiness. Estimation strategies that exploit the combination of lottery and non-lottery risk increase precision markedly. Grade A effects are similar when identified by screened and unscreened (lottery) tie-breakers and for screened and lottery schools. Selection bias in OLS estimates is egregious for Grade A screened schools. |
| Information | 英語での発表となります（Presentation in English） 主催：Microeconomics Workshop |