{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robust-causal-estimation-in-the-large-sample","title":"Robust Causal Estimation in the Large-Sample Limit without Strict Faithfulness","arxiv_id":"1704.01864","date":"2017-04-06","proceeding":null,"authors":["Ioan Gabriel Bucur","Tom Claassen","Tom Heskes"],"abstract":"Causal effect estimation from observational data is an important and much\nstudied research topic. The instrumental variable (IV) and local causal\ndiscovery (LCD) patterns are canonical examples of settings where a closed-form\nexpression exists for the causal effect of one variable on another, given the\npresence of a third variable. Both rely on faithfulness to infer that the\nlatter only influences the target effect via the cause variable. In reality, it\nis likely that this assumption only holds approximately and that there will be\nat least some form of weak interaction. This brings about the paradoxical\nsituation that, in the large-sample limit, no predictions are made, as\ndetecting the weak edge invalidates the setting. We introduce an alternative\napproach by replacing strict faithfulness with a prior that reflects the\nexistence of many 'weak' (irrelevant) and 'strong' interactions. We obtain a\nposterior distribution over the target causal effect estimator which shows\nthat, in many cases, we can still make good estimates. We demonstrate the\napproach in an application on a simple linear-Gaussian setting, using the\nMultiNest sampling algorithm, and compare it with established techniques to\nshow our method is robust even when strict faithfulness is violated.","url_abs":"http://arxiv.org/abs/1704.01864v1","url_pdf":"http://arxiv.org/pdf/1704.01864v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-causal-estimation-in-the-large-sample","repo_url":"https://github.com/igbucur/RoCELL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"causal-discovery","task_name":"Causal Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}