no code implementations • 11 Mar 2021 • Fredrik Sävje
This paper argues that the two roles exposure mappings currently serve can, and typically should, be separated, so that exposures are used to define effects without necessarily assuming that they are capturing the complete causal structure in the experiment.
Causal Inference Statistics Theory Econometrics Methodology Statistics Theory
1 code implementation • 8 Nov 2019 • Christopher Harshaw, Fredrik Sävje, Daniel Spielman, Peng Zhang
Asymptotically, the design perfectly balances all linear functions of a growing number of covariates with a diminishing reduction in robustness, effectively allowing experimenters to escape the compromise between balance and robustness in large samples.
Methodology Data Structures and Algorithms Statistics Theory Statistics Theory
no code implementations • 16 Jul 2019 • Fredrik Sävje
The paper shows that matching without replacement on propensity scores produces estimators that generally are inconsistent for the average treatment effect of the treated.