数据稀缺环境下的影响评估：以孟加拉国耐胁迫水稻品种为例

Journal of Development Economics · 2025 · [{"name": "Jeffrey D. Michler", "affiliation": ["University of Arizona"]}, {"name": "Dewan Abdullah Al Rafi", "affiliation": ["University of Idaho"]}, {"name": "Jonathan Giezendanner", "affiliation": ["Massachusetts Institute of Technology"]}, {"name": "Anna Josephson", "affiliation": ["University of Arizona"]}, {"name": "Valerien O. Pede", "affiliation": ["International Rice Research Institute"]}, {"name": "Beth Tellman", "affiliation": ["University of Wisconsin–Madison"]}]

中文摘要

新技术有时会在缺乏开展识别良好的影响评估所需数据的时间或地点被引入。我们开发了一种方法，将地球观测（EO）数据和深度学习与行政数据和调查数据相结合，使研究者能够在传统经济数据缺失时开展影响评估。为展示我们的方法，我们研究了15年前首次引入孟加拉国的耐逆水稻品种（stress tolerant rice varieties, STRVs）。利用覆盖全国、跨越二十年的水稻生产和洪水EO数据，我们发现了STRV有效性的证据。我们强调，该技术仅在一组特定条件下才有效这一性质，造成了一个EO数据特别适合处理的“金发姑娘问题”（Goldilocks Problem）。我们的发现回应了在数据稀缺环境中使用EO数据开展影响评估的前景与挑战。

Abstract

New technologies are sometimes introduced at times or in places that lack the necessary data to conduct a well-identified impact evaluation. We develop a methodology that combines Earth Observation (EO) data and deep learning with administrative and survey data so as to allow researchers to conduct impact evaluations when traditional economic data is missing. To demonstrate our method, we study stress tolerant rice varieties (STRVs) first introduced to Bangladesh 15 years ago. Using EO data on rice production and flooding for the entire country, spanning two decades, we find evidence of STRV effectiveness. We highlight how the nature of the technology, which is only effective under a specific set of circumstances, creates a Goldilocks Problem that EO data is particularly well suited to addressing. Our findings speak to the promises and challenges of using EO data to conduct impact evaluations in data-scarce environments.