-
Notifications
You must be signed in to change notification settings - Fork 96
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Doubly robust models renaming + multiple treatment-feature options (#28)
* Change `DoublyRobust` to `BaseDoublyRobust` * Change `DoublyRobustVanilla` to `ResidualCorrectedStandardization` * Change `DoublyRobustJoffe` to `WeightedStandardization` * Change `DoublyRobustIpFeature` to `PropensityFeatureStandardization` * Multiple treatment-based features in `PropensityFeatureStandardization` Adds several options for propensity features: 1. inverse-propensity weight: 1/Pr[A=a_i|X]. 2. inverse-propensity matrix: 1/Pr[A=a|X] for all possible `a`s. 3. propensity vector: Pr[A=1|X] 4. logit-transformed propensities: logit(Pr[A=1|X]) 5. propensity matrix: Pr[A=a|X] for all possible `a`s. Also adds corresponding tests for these options.
- Loading branch information
Showing
7 changed files
with
236 additions
and
89 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.