# What Makes Forest-Based Heterogeneous Treatment Effect Estimators Work?

arXiv: https://arxiv.org/abs/2206.10323 · HTML: https://mlsanity.com/paper/2206.10323/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 66 references that are in the map.
- First posted on arXiv 21 Jun 2022.

## Builds on (most cited first, 18 of 18)

- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [Quasi-Oracle Estimation of Heterogeneous Treatment Effects](https://mlsanity.com/paper/1712.04912/) (2017)
- [Generalized Random Forests](https://mlsanity.com/paper/1610.01271/) (2016)
- [Recursive Partitioning for Heterogeneous Causal Effects](https://mlsanity.com/paper/1504.01132/) (2015)
- [Tunability: Importance of Hyperparameters of Machine Learning Algorithms](https://mlsanity.com/paper/1802.09596/) (2018)
- [Hyperparameters and Tuning Strategies for Random Forest](https://mlsanity.com/paper/1804.03515/) (2018)
- [Estimating Treatment Effects with Causal Forests: An Application](https://mlsanity.com/paper/1902.07409/) (2019)
- [Some methods for heterogeneous treatment effect estimation in high-dimensions](https://mlsanity.com/paper/1707.00102/) (2017)
- [Estimating heterogeneous treatment effects with right-censored data via causal survival forests](https://mlsanity.com/paper/2001.09887/) (2020)
- [Random Forest Missing Data Algorithms](https://mlsanity.com/paper/1701.05305/) (2017)
- [Model-based Recursive Partitioning for Subgroup Analyses](https://mlsanity.com/paper/1605.04078/) (2016)
- [Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods](https://mlsanity.com/paper/1701.05306/) (2017)
- [Most Likely Transformations](https://mlsanity.com/paper/1508.06749/) (2015)
- [Distributional Regression Forests for Probabilistic Precipitation Forecasting in Complex Terrain](https://mlsanity.com/paper/1804.02921/) (2018)
- [Doubly robust treatment effect estimation with missing attributes](https://mlsanity.com/paper/1910.10624/) (2019)
- [Individual Treatment Effect Prediction for ALS Patients](https://mlsanity.com/paper/1604.08720/) (2016)
- [Survival Forests under Test: Impact of the Proportional Hazards Assumption on Prognostic and Predictive Forests for ALS Survival](https://mlsanity.com/paper/1902.01587/) (2019)

## Built on by (most cited first, 4 of 4)

- [Comparison of Methods that Combine Multiple Randomized Trials to Estimate Heterogeneous Treatment Effects](https://mlsanity.com/paper/2303.16299/) (2023)
- [Heterogeneous Treatment Effect Estimation for Observational Data using Model-based Forests](https://mlsanity.com/paper/2210.02836/) (2022)
- [Fairness Implications of Heterogeneous Treatment Effect Estimation with Machine Learning Methods in Policy-making](https://mlsanity.com/paper/2309.00805/) (2023)
- [Practical Guide for Causal Pathways and Sub-group Disparity Analysis](https://mlsanity.com/paper/2407.02702/) (2024)

## Abstract (arXiv)

Estimation of heterogeneous treatment effects (HTE) is of prime importance in many disciplines, ranging from personalized medicine to economics among many others. Random forests have been shown to be a flexible and powerful approach to HTE estimation in both randomized trials and observational studies. In particular "causal forests", introduced by Athey, Tibshirani and Wager (2019), along with the R implementation in package grf were rapidly adopted. A related approach, called "model-based forests", that is geared towards randomized trials and simultaneously captures effects of both prognostic and predictive variables, was introduced by Seibold, Zeileis and Hothorn (2018) along with a modular implementation in the R package model4you. Here, we present a unifying view that goes beyond the theoretical motivations and investigates which computational elements make causal forests so successful and how these can be blended with the strengths of model-based forests. To do so, we show that both methods can be understood in terms of the same parameters and model assumptions for an additive model under L2 loss. This theoretical insight allows us to implement several flavors of "model-based causal forests" and dissect their different elements in silico. The original causal forests and model-based forests are compared with the new blended versions in a benchmark study exploring both randomized trials and observational settings. In the randomized setting, both approaches performed akin. If confounding was present in the data generating process, we found local centering of the treatment indicator with the corresponding propensities to be the main driver for good performance. Local centering of the outcome was less important, and might be replaced or enhanced by simultaneous split selection with respect to both prognostic and predictive effects.