Package: grf 2.6.1

grf: Generalized Random Forests

Forest-based statistical estimation and inference. GRF provides non-parametric methods for heterogeneous treatment effects estimation (optionally using right-censored outcomes, multiple treatment arms or outcomes, or instrumental variables), as well as least-squares regression, quantile regression, and survival regression, all with support for missing covariates.

Authors:Julie Tibshirani [aut], Susan Athey [aut], Rina Friedberg [ctb], Vitor Hadad [ctb], David Hirshberg [ctb], Luke Miner [ctb], Erik Sverdrup [aut, cre], Stefan Wager [aut], Marvin Wright [ctb]

grf_2.6.1.tar.gz
grf_2.6.1.zip(r-4.7)grf_2.6.1.zip(r-4.6)grf_2.6.1.zip(r-4.5)
grf_2.6.1.tgz(r-4.6-x86_64)grf_2.6.1.tgz(r-4.6-arm64)grf_2.6.1.tgz(r-4.5-x86_64)grf_2.6.1.tgz(r-4.5-arm64)
grf_2.6.1.tar.gz(r-4.7-arm64)grf_2.6.1.tar.gz(r-4.7-x86_64)grf_2.6.1.tar.gz(r-4.6-arm64)grf_2.6.1.tar.gz(r-4.6-x86_64)
grf_2.6.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
grf/json (API)

# Install 'grf' in R:

install.packages('grf', repos = c('https://anumbat.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/grf-labs/grf/issues

Uses libs:

c++– GNU Standard C++ Library v3

Datasets:

attentionrct - Payday cognitive attention experiment
schoolrct - Brazilian high school financial education RCT

On CRAN:

cpp

7.58 score 27 packages 2.3k scripts 10k downloads 1 mentions 27 exports 8 dependencies

Last updated from:4cfeab8ee3. Checks:11 WARNING, 2 OK. Indexed: yes.

Target	Result	Time
linux-devel-arm64	WARNING	386
linux-devel-x86_64	WARNING	388
source / vignettes	OK	551
linux-release-arm64	WARNING	404
linux-release-x86_64	WARNING	396
macos-release-arm64	WARNING	180
macos-release-x86_64	WARNING	458
macos-oldrel-arm64	WARNING	375
macos-oldrel-x86_64	WARNING	441
windows-devel	WARNING	329
windows-release	WARNING	301
windows-oldrel	WARNING	361
wasm-release	OK	378

Exports:average_treatment_effect best_linear_projection boosted_regression_forest causal_forest causal_survival_forest generate_causal_data generate_causal_survival_data get_forest_weights get_leaf_node get_scores get_tree grf_options instrumental_forest ll_regression_forest lm_forest merge_forests multi_arm_causal_forest multi_regression_forest probability_forest quantile_forest rank_average_treatment_effect rank_average_treatment_effect.fit regression_forest split_frequencies survival_forest test_calibration variable_importance

Dependencies:DiceKriging lattice lmtest Matrix Rcpp RcppEigen sandwich zoo

An introduction to grf

Rendered fromgrf_guide.Rmdusingknitr::rmarkdown

Last update: 2026-03-03
Started: 2026-03-03

Help page	Topics
Payday cognitive attention experiment	attentionrct
Get doubly robust estimates of average treatment effects.	average_treatment_effect
Estimate the best linear projection of a conditional average treatment effect.	best_linear_projection
Boosted regression forest	boosted_regression_forest
Causal forest	causal_forest
Causal survival forest	causal_survival_forest
Generate causal forest data	generate_causal_data
Simulate causal survival data	generate_causal_survival_data
Given a trained forest and test data, compute the kernel weights for each test point.	get_forest_weights
Find the leaf node for a test sample.	get_leaf_node
Compute doubly robust scores for a GRF forest object	get_scores
Compute doubly robust scores for a causal forest.	get_scores.causal_forest
Compute doubly robust scores for a causal survival forest.	get_scores.causal_survival_forest
Doubly robust scores for estimating the average conditional local average treatment effect.	get_scores.instrumental_forest
Compute doubly robust scores for a multi arm causal forest.	get_scores.multi_arm_causal_forest
Retrieve a single tree from a trained forest object.	get_tree
grf package options	grf_options
Intrumental forest	instrumental_forest
Local linear forest	ll_regression_forest
LM Forest	lm_forest
Merges a list of forests that were grown using the same data into one large forest.	merge_forests
Multi-arm/multi-outcome causal forest	multi_arm_causal_forest
Multi-task regression forest	multi_regression_forest
Plot a GRF tree object.	plot.grf_tree
Plot the Targeting Operator Characteristic curve.	plot.rank_average_treatment_effect
Predict with a boosted regression forest.	predict.boosted_regression_forest
Predict with a causal forest	predict.causal_forest
Predict with a causal survival forest forest	predict.causal_survival_forest
Predict with an instrumental forest	predict.instrumental_forest
Predict with a local linear forest	predict.ll_regression_forest
Predict with a lm forest	predict.lm_forest
Predict with a multi arm causal forest	predict.multi_arm_causal_forest
Predict with a multi regression forest	predict.multi_regression_forest
Predict with a probability forest	predict.probability_forest
Predict with a quantile forest	predict.quantile_forest
Predict with a regression forest	predict.regression_forest
Predict with a survival forest	predict.survival_forest
Print a boosted regression forest	print.boosted_regression_forest
Print a GRF forest object.	print.grf
Print a GRF tree object.	print.grf_tree
Print the Rank-Weighted Average Treatment Effect (RATE).	print.rank_average_treatment_effect
Print tuning output. Displays average error for q-quantiles of tuned parameters.	print.tuning_output
Probability forest	probability_forest
Quantile forest	quantile_forest
Estimate a Rank-Weighted Average Treatment Effect (RATE).	rank_average_treatment_effect
Fitter function for Rank-Weighted Average Treatment Effect (RATE).	rank_average_treatment_effect.fit
Regression forest	regression_forest
Brazilian high school financial education RCT	schoolrct
Calculate which features the forest split on at each depth.	split_frequencies
Survival forest	survival_forest
Omnibus evaluation of the quality of the random forest estimates via calibration.	test_calibration
Calculate a simple measure of 'importance' for each feature.	variable_importance

Package: grf 2.6.1

grf: Generalized Random Forests

Citation

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)