Decision-Theoretic Causal Diagnostics via Le Cam Deficiency R package causaldef version 0.2.0 Implements Le Cam deficiency theory for causal inference, as described in Akdemir (2026) <doi:10.5281/zenodo.18367347>. Provides theorem-backed bounds together with computable proxy diagnostics for information loss from confounding, selection bias, and distributional shift. Supports continuous, binary, count, survival, and competing risks outcomes. Key features include propensity-score total-variation deficiency proxies, negative control diagnostics, policy regret bounds, and sensitivity analysis via confounding frontiers. Software Depends: R (>= 3.6.0) Imports: checkmate, cli, ggplot2, stats, graphics Suggests: survival, MatchIt, tmle, SuperLearner, grf, future.apply, glue, shiny, plumber, jsonlite, cmprsk, testthat (>= 3.0.0), knitr, rmarkdown Deniz Akdemir <deniz.akdemir.work@gmail.com> Comprehensive R Archive Network (CRAN) Deniz Akdemir [aut, cre] MIT + file LICENSE (https://CRAN.R-project.org/package=causaldef/LICENSE) 2026-03-31 application/tgz https://CRAN.R-project.org/package=causaldef doi:10.32614/CRAN.package.causaldef en-US