UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Causal Inference through a Witness Protection Program

Silva, R; Evans, R; (2016) Causal Inference through a Witness Protection Program. Journal of Machine Learning Research , 17 , Article 56. Green open access

Silva and Ricardo Causal inference through a witness protection program VoR.pdf

Download (612kB) | Preview


One of the most fundamental problems in causal inference is the estimation of a causal effect when treatment and outcome are confounded. This is difficult in an observational study, because one has no direct evidence that all confounders have been adjusted for. We introduce a novel approach for estimating causal effects that exploits observational conditional independencies to suggest \weak" paths in an unknown causal graph. The widely used faithfulness condition of Spirtes et al. is relaxed to allow for varying degrees of "path cancellations" that imply conditional independencies but do not rule out the existence of confounding causal paths. The output is a posterior distribution over bounds on the average causal effect via a linear programming approach and Bayesian inference. We claim this approach should be used in regular practice as a complement to other tools in observational studies.

Type: Article
Title: Causal Inference through a Witness Protection Program
Open access status: An open access version is available from UCL Discovery
Publisher version: http://www.jmlr.org/papers/v17/15-130.html
Language: English
Additional information: Copyright © 2016 Ricardo Silva and Robin Evans
Keywords: Causal inference, instrumental variables, Bayesian inference, linear programming
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
URI: https://discovery.ucl.ac.uk/id/eprint/1471797
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item