Unbiased Estimation of the Average Treatment Effect in Cluster-Randomized Experiments
By J. Middleton, P. M. Aronow. 2015
85 citations recorded by the source corpus.
Subfields: Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/1128add4b674954c2735afa589c5122cb0115467
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Statistics and Probability
Citations in the corpus
- Decomposing Treatment Effect Variation (2016, methodology): “Using the mathematical framework introduced in the Appendix and in Li and Ding (2017), we can easily generalize Theorem 1 to more complicated experimental designs, for example, cluster-randomized trials (Middleton and Aronow 2015) and unbalanced 22 split-plot designs (Zhao et al.”
- General Forms of Finite Population Central Limit Theorems with Applications to Causal Inference (2016, background): “Middleton and Aronow (2015) showed that ̂(γ1, γ0) is unbiased for τ when γ1 = γ0 and they are both predetermined constant vectors.”
- Covariate-adjusted Fisher randomization tests for the average treatment effect (2020, background): “…expression of τ from (2), suggests the equivalence of (Zi, Ỹi·, x̃i·) M i=1 to data from a complete randomization with potential outcomes {Ỹi·(1), Ỹi·(0)} and average treatment effect τ (Middleton and Aronow 2015; Li and Ding 2017), and allows us to derive results in parallel with Theorems 1–4.”
- Do Online Advertisements Increase Political Candidates’ Name Recognition or Favorability? Evidence from Randomized Field Experiments (2014, methodology): “subjects to treatment and control (Middleton and Aronow 2011), clustered assignment imposes no additional assumptions beyond those invoked by experiments randomized at the individual level; the main complication associated with clustered designs is proper estimation of sampling variability (Arceneau”
- Bridging Finite and Super Population Causal Inference (2017, background): “If the causal parameters can be expressed as cluster-level outcomes, then the result can be straightforwardly applied (cf. Aronow and Middleton 2013; Middleton and Aronow 2015).”
- A Class of Unbiased Estimators of the Average Treatment Effect in Randomized Experiments (2013, methodology): “These results extend those of Middleton and Aronow [5], which provides unbiased estimators for experiments with complete randomization of clusters, including linear covariate adjustment.”
- Randomization Tests for Weak Null Hypotheses in Randomized Experiments (2018, background): “Middleton and Aronow (2015) stressed that we cannot implement the same analysis as if we had a CRE on the N units.”