Identification of Treatment Effects Under Conditional Partial Independence
By Matthew A. Masten, Alexandre Poirier. 2017
58 citations recorded by the source corpus.
Conditional independence of treatment assignment from potential outcomes is a commonly used but nonrefutable assumption. We derive identified sets for various treatment effect parameters under nonparametric deviations from this conditional independence assumption. These deviations are defined via a conditional treatment assignment probability, which makes it straightforward to interpret. Our results can be used to assess the robustness of empirical conclusions obtained under the baseline conditional independence assumption.
Subfields: Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/c69a653e33c54e68138d712b002cf7057498e977
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
- Angela Zhou
- Nathan Kallus
- Kevin Guo
- Jacob Dorn
- Stefan Wager
- Susan Athey
- Andrew Bennett
- Masatoshi Uehara
Citations in the corpus
- Confounding-Robust Policy Improvement (2018, background): “Masten and Poirier (2018) consider sup-norm bounds on propensity differences and show sharp partial identification of bounds for CATE and ATE by integrating partially identified bounds on the conditional quantile treatment effect.”
- Sharp Sensitivity Analysis for Inverse Propensity Weighting via Quantile Balancing (2021, background): “For alternative sensitivity assumptions, sharp bounds often involve distinct quantiles Q τ( x ) for each covariate level (Lee 2009; Masten and Poirier 2018), complicating estimation by potentially requiring estimates of the entire conditional quantile process (Masten, Poirier, and Zhang 2020;…”