Bayesian additive regression trees for causal inference with multiple treatments

Michael Lopez (with Liangyuan Hu, Chenyang Gu)

BART with multiple treatments

Michael Lopez, Liangyuan Hu, Chenyang Gu https://github.com/statsbylopez/ci-bart

The setting: 3 prostate cancer treatments

Treatment n Death Rate
Prostatectomy 15435 0.094
RT 1 24688 0.029
RT 2 2642 0.061

The setting: 3 prostate cancer treatments

Issue 1: Selection bias

Issue 2: Non-overlapping distributions

Issue 3: Large weights

Issue 3: Large weights

Notation

Consider causal effect of \(A \in \{1, \ldots, Z\}\) on binary outcome \(Y \in \{0,1\}\)

Notation

Interest: average treatment effect among treated

Causal inference with multiple treatments

Why not binary approaches?

Causal inference with multiple treatments

Bayesian Additive Regression Trees

BART model:

Bayesian Additive Regression Trees

Why BART for causal inference? see Hill, 2012

Bayesian Additive Regression Trees

Why BART for multiple treatments?

Simulation study

6 factorial design using dbarts package in R

Simulation results

3 prostate cancer treatments

ATT’s: generalizable to population receiving RT 1

Comments

Comments

Github site: https://github.com/statsbylopez/ci-bart

Twitter: @statsbylopez