?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Causal+Inference+through+a+Witness+Protection+Program&rft.creator=Silva%2C+R&rft.creator=Evans%2C+R&rft.description=One+of+the+most+fundamental+problems+in+causal+inference+is+the+estimation+of+a+causal+effect+when+variables+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+a+unknown+causal+graph.+The+widely+used+faithfulness+condition+of+Spirtes+et+al.+is+relaxed+to+allow+for+varying+degrees+of+path+cancellations''+that+will+imply+conditional+independencies+but+do+not+rule+out+the+existence+of+confounding+causal+paths.+The+outcome+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+to+complement+other+default+tools+in+observational+studies.&rft.subject=causality%2C+Bayesian+inference%2C+linear+programming&rft.publisher=Neural+Information+Processing+Systems+Foundation&rft.contributor=Gharamani%2C+Z&rft.contributor=Welling%2C+W&rft.contributor=Cortes%2C+C&rft.contributor=Lawrence%2C+ND&rft.contributor=Weinberger%2C+KQ&rft.date=2014-12-13&rft.type=Proceedings+paper&rft.publisher=NIPS+2014&rft.language=eng&rft.source=+++++In%3A+Gharamani%2C+Z+and+Welling%2C+W+and+Cortes%2C+C+and+Lawrence%2C+ND+and+Weinberger%2C+KQ%2C+(eds.)+Advances+in+Neural+Information+Processing+Systems+27+(NIPS+2014).++++Neural+Information+Processing+Systems+Foundation%3A+Montreal%2C+Canada.+(2014)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F1471795%2F1%2F5602-causal-inference-through-a-witness-protection-program.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F1471795%2F&rft.rights=open