Gateway to Think Tanks
来源类型 | Discussion paper |
规范类型 | 论文 |
来源ID | DP16788 |
DP16788 Belief Convergence under Misspecified Learning: A Martingale Approach | |
Mira Frick; Yuhta Ishii | |
发表日期 | 2021-12-07 |
出版年 | 2021 |
语种 | 英语 |
摘要 | We present an approach to analyze learning outcomes in a broad class of misspecified environments, spanning both single-agent and social learning. We introduce a novel “prediction accuracy” order over subjective models, and observe that this makes it possible to partially restore standard martingale convergence arguments that apply under correctly specified learning. Based on this, we derive general conditions to determine when beliefs in a given environment converge to some long-run belief either locally or globally (i.e., from some or all initial beliefs). We show that these conditions can be applied, first, to unify and generalize various convergence results in previously studied settings. Second, they enable us to analyze environments where learning is “slow,” such as costly information acquisition and sequential social learning. In such environments, we illustrate that even if agents learn the truth when they are correctly specified, vanishingly small amounts of misspecification can generate extreme failures of learning. |
主题 | Organizational Economics |
URL | https://cepr.org/publications/dp16788 |
来源智库 | Centre for Economic Policy Research (United Kingdom) |
资源类型 | 智库出版物 |
条目标识符 | http://119.78.100.153/handle/2XGU8XDN/545720 |
推荐引用方式 GB/T 7714 | Mira Frick,Yuhta Ishii. DP16788 Belief Convergence under Misspecified Learning: A Martingale Approach. 2021. |
条目包含的文件 | 条目无相关文件。 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Mira Frick]的文章 |
[Yuhta Ishii]的文章 |
百度学术 |
百度学术中相似的文章 |
[Mira Frick]的文章 |
[Yuhta Ishii]的文章 |
必应学术 |
必应学术中相似的文章 |
[Mira Frick]的文章 |
[Yuhta Ishii]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。