Causal Inference with the Instrumental Variable Approach and Bayesian Nonparametric Machine Learning

Add code
Feb 01, 2021
Robert E. McCulloch, Rodney A. Sparapani, Brent R. Logan, Purushottam W. Laud
Figure 1 for Causal Inference with the Instrumental Variable Approach and Bayesian Nonparametric Machine Learning
Figure 2 for Causal Inference with the Instrumental Variable Approach and Bayesian Nonparametric Machine Learning
Figure 3 for Causal Inference with the Instrumental Variable Approach and Bayesian Nonparametric Machine Learning
Figure 4 for Causal Inference with the Instrumental Variable Approach and Bayesian Nonparametric Machine Learning

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We provide a new flexible framework for inference with the instrumental variable model. Rather than using linear specifications, functions characterizing the effects of instruments and other explanatory variables are estimated using machine learning via Bayesian Additive Regression Trees (BART). Error terms and their distribution are inferred using Dirichlet Process mixtures. Simulated and real examples show that when the true functions are linear, little is lost. But when nonlinearities are present, dramatic improvements are obtained with virtually no manual tuning.

* 33 pages, 7 figures  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon