| 来源类型 | Working Paper |
| 规范类型 | 报告 |
| DOI | 10.3386/w30108 |
| 来源ID | Working Paper 30108 |
| Contamination Bias in Linear Regressions | |
| Paul Goldsmith-Pinkham; Peter Hull; Michal Kolesár | |
| 发表日期 | 2022-06-06 |
| 出版年 | 2022 |
| 语种 | 英语 |
| 摘要 | We study regressions with multiple treatments and a set of controls that is flexible enough to purge omitted variable bias. We show these regressions generally fail to estimate convex averages of heterogeneous treatment effects; instead, estimates of each treatment’s effect are contaminated by non-convex averages of the effects of other treatments. We discuss three estimation approaches that avoid such contamination bias, including a new estimator of efficiently weighted average effects. We find minimal bias in a re-analysis of Project STAR, due to idiosyncratic effect heterogeneity. But sizeable contamination bias arises when effect heterogeneity becomes correlated with treatment propensity scores. |
| 主题 | Econometrics ; Estimation Methods ; Experimental Design |
| URL | https://www.nber.org/papers/w30108 |
| 来源智库 | National Bureau of Economic Research (United States) |
| 引用统计 | |
| 资源类型 | 智库出版物 |
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/587781 |
| 推荐引用方式 GB/T 7714 | Paul Goldsmith-Pinkham,Peter Hull,Michal Kolesár. Contamination Bias in Linear Regressions. 2022. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 资源类型 | 版本类型 | 开放类型 | 使用许可 | ||
| w30108.pdf（587KB） | 智库出版物 | 限制开放 | CC BY-NC-SA | 浏览 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
