Silva, R;
Evans, R;
(2016)
Causal Inference through a Witness Protection Program.
Journal of Machine Learning Research
, 17
, Article 56.
Preview |
Text
Silva and Ricardo Causal inference through a witness protection program VoR.pdf Download (612kB) | Preview |
Abstract
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 UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/1471797 |
Archive Staff Only
View Item |