published in: Econometrica; 2017, 85 (2), 645 - 660
Estimators of average treatment effects under unconfounded treatment assignment are known to become rather imprecise if there is limited overlap in the covariate distributions between the treatment groups. But such limited overlap can also have a detrimental effect on inference, and lead for example to highly distorted confidence intervals.
This paper shows that this is because the coverage error of traditional confidence intervals is not so much driven by the total sample size, but by the number of observations in the areas of limited overlap. At least some of these "local sample sizes" are often very small in applications, up to the point where distributional approximation derived from the Central Limit Theorem become unreliable. Building on this observation, the paper proposes two new robust confidence intervals that are extensions of classical approaches to small sample inference. It shows that these approaches are easy to implement, and have superior theoretical and practical properties relative to standard methods in empirically relevant settings. They should thus be useful for practitioners.
We use cookies to provide you with an optimal website experience. This includes cookies that are necessary for the operation of the site as well as cookies that are only used for anonymous statistical purposes, for comfort settings or to display personalized content. You can decide for yourself which categories you want to allow. Please note that based on your settings, you may not be able to use all of the site's functions.
Cookie settings
These necessary cookies are required to activate the core functionality of the website. An opt-out from these technologies is not available.
In order to further improve our offer and our website, we collect anonymous data for statistics and analyses. With the help of these cookies we can, for example, determine the number of visitors and the effect of certain pages on our website and optimize our content.