mixedsubjects: Causal Inference in Experiments with Mixed-Subjects Designs

Implements seven estimators for average treatment effect (ATE) estimation in mixed-subjects designs (MSDs), where human subjects data is augmented with predictions from large language models (LLMs). Includes Difference-in-Means, GREG, PPI++, Doubly-Tuned, Difference-in-Predictions (DiP), DiP++, and D-T DiP estimators. Provides point estimates, variance estimation via delta-method or bootstrap, and optimal design selection for budget allocation between human observations and LLM predictions.

Version:	1.0.0
Imports:	stats
Suggests:	knitr, rmarkdown, testthat (≥ 3.0.0)
Published:	2026-07-02
DOI:	10.32614/CRAN.package.mixedsubjects
Author:	Austin van Loon [aut], Klint Kanopka [aut, cre], Yuan Huang [ctb]
Maintainer:	Klint Kanopka <klint.kanopka at nyu.edu>
BugReports:	https://github.com/klintkanopka/mixedsubjects/issues
License:	MIT + file LICENSE
URL:	https://klintkanopka.com/mixedsubjects/
NeedsCompilation:	no
Materials:	README, NEWS
CRAN checks:	mixedsubjects results

Documentation:

Reference manual:	mixedsubjects.html , mixedsubjects.pdf
Vignettes:	Comparing Estimators Under Different Data-Generating Processes (source, R code) Introduction to Mixed-Subjects Designs with the mixedsubjects Package (source, R code)

Downloads:

Package source:	mixedsubjects_1.0.0.tar.gz
Windows binaries:	r-devel: mixedsubjects_1.0.0.zip, r-release: mixedsubjects_1.0.0.zip, r-oldrel: mixedsubjects_1.0.0.zip
macOS binaries:	r-release (arm64): mixedsubjects_1.0.0.tgz, r-oldrel (arm64): mixedsubjects_1.0.0.tgz, r-release (x86_64): mixedsubjects_1.0.0.tgz, r-oldrel (x86_64): mixedsubjects_1.0.0.tgz

Linking:

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