no code implementations • 27 Jul 2023 • Yuehao Bai, Jizhou Liu, Azeem M. Shaikh, Max Tabord-Meehan
By a "finely stratified" design, we mean experiments in which units are divided into groups of a fixed size and a proportion within each group is assigned to treatment uniformly at random so that it respects the restriction on the marginal probability of treatment assignment.
no code implementations • 24 Jul 2023 • Yuehao Bai, Hongchang Guo, Azeem M. Shaikh, Max Tabord-Meehan
To this end, we derive the limiting behavior of a two-stage least squares estimator of the local average treatment effect which includes both the additional covariates in addition to pair fixed effects, and show that the limiting variance is always less than or equal to that of the Wald estimator.
no code implementations • 9 Feb 2023 • Yuehao Bai, Liang Jiang, Joseph P. Romano, Azeem M. Shaikh, Yichong Zhang
This paper studies inference on the average treatment effect in experiments in which treatment status is determined according to "matched pairs" and it is additionally desired to adjust for observed, baseline covariates to gain further precision.
no code implementations • 27 Nov 2022 • Yuehao Bai, Jizhou Liu, Azeem M. Shaikh, Max Tabord-Meehan
Here, by a cluster randomized experiment, we mean one in which treatment is assigned at the level of the cluster; by a "matched pairs'' design we mean that a sample of clusters is paired according to baseline, cluster-level covariates and, within each pair, one cluster is selected at random for treatment.
no code implementations • 23 Sep 2022 • Yuehao Bai, Meng Hsuan Hsieh, Jizhou Liu, Max Tabord-Meehan
To address these claims, we derive the estimands obtained from the difference-in-means estimator in a matched-pair design both when the observations from pairs with an attrited unit are retained and when they are dropped.
no code implementations • 15 Jun 2022 • Yuehao Bai
In randomized controlled trials (RCTs), treatment is often assigned by stratified randomization.
no code implementations • 8 Jun 2022 • Yuehao Bai, Jizhou Liu, Max Tabord-Meehan
Leveraging our previous results, we establish that our estimator achieves a lower asymptotic variance under the fully-blocked design than that under any stratified factorial design which stratifies the experimental sample into a finite number of "large" strata.