Functional Restriction and Efficiency in Causal Inference

73 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference (2017, methodology): “These methods can be augmented with variable selection procedures at either or both steps of the estimation procedure, which can improve estimation but at a potential further sacrifice of interpretability (Brookhart et al., 2006; Hahn, 2004).”
Robust Estimation of Causal Effects via High-Dimensional Covariate Balancing Propensity Score. (2018, methodology): “Our variance bound V is different from the “oracle efficiency bound,” which is the semi- 305 parametric variance bound with the known support of the propensity score and outcome models (Hahn, 2004).”
On model selection and model misspecification in causal inference (2012, unknown): “Second, it has been documented that efficiency gains may be realised when a priori knowledge is available that given covariates are only associated with the exposure, but have no residual association with outcome.(25) However, in practice, such a priori information is rarely, if ever, available.”