A Bayesian nonparametric approach to causal inference on quantiles

Dandan Xu, Michael J. Daniels and Almut G. Winterstein

Biometrics, 2018, vol. 74, issue 3, 986-996

Abstract: We propose a Bayesian nonparametric approach (BNP) for causal inference on quantiles in the presence of many confounders. In particular, we define relevant causal quantities and specify BNP models to avoid bias from restrictive parametric assumptions. We first use Bayesian additive regression trees (BART) to model the propensity score and then construct the distribution of potential outcomes given the propensity score using a Dirichlet process mixture (DPM) of normals model. We thoroughly evaluate the operating characteristics of our approach and compare it to Bayesian and frequentist competitors. We use our approach to answer an important clinical question involving acute kidney injury using electronic health records.

Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
https://doi.org/10.1111/biom.12863

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bla:biomet:v:74:y:2018:i:3:p:986-996

Ordering information: This journal article can be ordered from
http://www.blackwell ... bs.asp?ref=0006-341X

Access Statistics for this article

More articles in Biometrics from The International Biometric Society
Bibliographic data for series maintained by Wiley Content Delivery ().