MLCausal: Causal Inference Methods for Multilevel and Clustered Data

Provides an end-to-end workflow for estimating average treatment effects in clustered (multilevel) observational data. Core functionality includes cluster-aware propensity score estimation using fixed effects and Mundlak-style specifications, inverse probability weighting, within-cluster nearest-neighbor matching, covariate balance diagnostics at both individual and cluster-mean levels, outcome regression with cluster-robust standard errors, propensity score overlap visualization, and tipping-point sensitivity analysis for omitted cluster-level confounding.

Version:	0.1.0
Depends:	R (≥ 4.1.0)
Imports:	stats, sandwich (≥ 3.0-0), lmtest (≥ 0.9-38), ggplot2 (≥ 3.3.0), rlang (≥ 0.4.0)
Suggests:	testthat (≥ 3.0.0), knitr (≥ 1.36), rmarkdown (≥ 2.11)
Published:	2026-04-15
DOI:	10.32614/CRAN.package.MLCausal (may not be active yet)
Author:	Subir Hait [aut, cre]
Maintainer:	Subir Hait <haitsubi at msu.edu>
BugReports:	https://github.com/causalfragility-lab/MLCausal/issues
License:	MIT + file LICENSE
URL:	https://github.com/causalfragility-lab/MLCausal
NeedsCompilation:	no
Citation:	MLCausal citation info
Materials:	README
CRAN checks:	MLCausal results

Documentation:

Reference manual:	MLCausal.html , MLCausal.pdf
Vignettes:	Introduction to MLCausal (source, R code)

Downloads:

Package source:	MLCausal_0.1.0.tar.gz
Windows binaries:	r-devel: not available, r-release: MLCausal_0.1.0.zip, r-oldrel: not available
macOS binaries:	r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): not available, r-oldrel (x86_64): not available

Linking:

Please use the canonical form https://CRAN.R-project.org/package=MLCausal to link to this page.