更改

为了设计一个自然实验，研究小组研究了马萨诸塞州的彩票中奖者，这些中奖者多年来获得递增的奖金，而不是一次性的奖金。在这一过程中，研究小组能够研究稳定额外收入的因果效应。他们发现中奖对人们工作时间的影响很小。连续20年每年获得8万美元奖金的获奖者一定程度上减少了工作时间，但连续20年每年获得1.5万美元奖金的获奖者却没有因获得稳定额外收入而减少工作时间。在购买彩票的失业人员中，中奖者在购买彩票后的六年中参加工作的人数超过非中奖者。

为了设计一个自然实验，研究小组研究了马萨诸塞州的彩票中奖者，这些中奖者多年来获得递增的奖金，而不是一次性的奖金。在这一过程中，研究小组能够研究稳定额外收入的因果效应。他们发现中奖对人们工作时间的影响很小。连续20年每年获得8万美元奖金的获奖者一定程度上减少了工作时间，但连续20年每年获得1.5万美元奖金的获奖者却没有因获得稳定额外收入而减少工作时间。在购买彩票的失业人员中，中奖者在购买彩票后的六年中参加工作的人数超过非中奖者。

Some of Imbens' work was summarized in a book co-written with American statistician [[Donald Rubin|Donald B. Rubin]], ''Causal Inference for Statistics, Social, and Biomedical Sciences.<ref name=":1" />''

'''Some of Imbens' work was summarized in a book co-written with American statistician [[Donald Rubin|Donald B. Rubin]], ''Causal Inference for Statistics, Social, and Biomedical Sciences.<ref name=":1" />'''''

Some of Imbens' work was summarized in a book co-written with American statistician Donald B. Rubin, Causal Inference for Statistics, Social, and Biomedical Sciences.

'''Some of Imbens' work was summarized in a book co-written with American statistician Donald B. Rubin, Causal Inference for Statistics, Social, and Biomedical Sciences.'''

的一些工作被总结在一本书中，这本书是与美国统计学家 Donald b. Rubin 合著的，书名是《统计、社会和生医科学的因果推断》。

'''的一些工作被总结在一本书中，这本书是与美国统计学家 Donald b. Rubin 合著的，书名是《统计、社会和生医科学的因果推断》。'''

More recently, he (along with Prof. Susan Athey) has been working on using machine learning methods, particularly modifications to random forests called causal forests<ref>{{cite web |title=Causal Tree R package; Authors -- Susan Athey, Guido Imbens, Yangyang Kong & Vikas Ramachandra  |url=https://github.com/susanathey/causalTree/blob/master/doc/briefintro.pdf}}</ref><ref>{{cite web |title=Recursive partitioning for heterogeneous causal effects; Authors -- Susan Athey and Guido Imbens |url=https://www.pnas.org/content/113/27/7353.short |access-date=13 October 2021 |archive-date=29 July 2021 |archive-url=https://web.archive.org/web/20210729101951/https://www.pnas.org/content/113/27/7353.short |url-status=live }}</ref> to estimate heterogeneous treatment effects in causal inference models.

More recently, he (along with Prof. Susan Athey) has been working on using machine learning methods, particularly modifications to random forests called causal forests<ref>{{cite web |title=Causal Tree R package; Authors -- Susan Athey, Guido Imbens, Yangyang Kong & Vikas Ramachandra  |url=https://github.com/susanathey/causalTree/blob/master/doc/briefintro.pdf}}</ref><ref>{{cite web |title=Recursive partitioning for heterogeneous causal effects; Authors -- Susan Athey and Guido Imbens |url=https://www.pnas.org/content/113/27/7353.short |access-date=13 October 2021 |archive-date=29 July 2021 |archive-url=https://web.archive.org/web/20210729101951/https://www.pnas.org/content/113/27/7353.short |url-status=live }}</ref> to estimate heterogeneous treatment effects in causal inference models.