Crandore Hub

causalWins

Compute the Causal Win Ratio Using Nearest Neighbor Matching

Based on “Rethinking the Win Ratio: A Causal Framework for Hierarchical Outcome Analysis” (M. Even and J. Josse, 2025), this package provides implementations of three approaches - nearest neighbor matching, distributional regression forests, and efficient influence functions - to estimate the causal win ratio, win proportion, and net benefit.

Versions across snapshots

VersionRepositoryFileSize
0.1.0 rolling source/ R- causalWins_0.1.0.tar.gz 302.5 KiB
0.1.0 rolling linux/jammy R-4.5 causalWins_0.1.0.tar.gz 218.4 KiB
0.1.0 rolling linux/noble R-4.5 causalWins_0.1.0.tar.gz 218.4 KiB
0.1.0 latest source/ R- causalWins_0.1.0.tar.gz 302.5 KiB
0.1.0 latest linux/jammy R-4.5 causalWins_0.1.0.tar.gz 218.4 KiB
0.1.0 latest linux/noble R-4.5 causalWins_0.1.0.tar.gz 218.4 KiB
0.1.0 2026-04-23 source/ R- causalWins_0.1.0.tar.gz 302.5 KiB

Dependencies (latest)

Imports

Suggests