{"type":"ScholarlyArticle","title":"Proportion-based Sensitivity Analysis of Uncontrolled Confounding Bias in Causal Inference","authors":[{"name":"Haruka Yoshida","slug":"haruka-yoshida","given":"Haruka","family":"Yoshida","affiliation":"Graduate School of Engineering Science , Yokohama National University"},{"name":"Manabu Kuroki","slug":"manabu-kuroki","given":"Manabu","family":"Kuroki","affiliation":"Graduate School of Engineering Science , Yokohama National University"}],"abstract":"Uncontrolled confounding bias causes a spurious relationship between an exposure variable and an outcome variable and precludes reliable evaluation of the causal effect from observed data.Thus, it is important to observe a sufficient set of confounders to reliably evaluate the causal effect.However, there is no statistical method for judging whether an available set of covariates is sufficient to derive a reliable estimator for the causal effect.To address this problem, we focus on the fact that the mean squared error (MSE) of the outcome variable with respect to the average causal risk can be described as the sum of \"the conditional variance of the outcome variable given the exposure variable\" and \"the square of the uncontrolled confounding bias\".We then propose a novel sensitivity analysis, namely, the proportion-based sensitivity analysis of uncontrolled confounding bias in causal effects (PSA) in which the sensitivity parameter is formulated as the proportion of \"the square of the uncontrolled confounding bias\" to the MSE, and we clarify some properties.We also demonstrate the applicability of the PSA through two case studies.","doi":"10.24963/ijcai.2024/789","url":"https://ijcai.org/proceedings/2024/789","pdf":"https://ijcai.org/proceedings/2024/0789.pdf","markdown":"https://ijcai.org/proceedings/2024/789.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/789","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Uncertainty in AI","track":"Main Track","number":789,"pages":{"first":7136,"last":7143},"keywords":["Uncertainty in AI: UAI: Causality, structural causal models and causal inference"],"videos":[],"references":[{"position":1,"raw":"[Balke and Pearl, 1997] Alexander Balke and Judea Pearl. Bounds on treatment effects from studies with imperfect compliance. Journal of the American Statistical Associa- tion, 92(439):1171-1176, 1997.","title":"Bounds on treatment effects from studies with imperfect compliance","authors":"Pearl ; Balke, Alexander Balke, Judea Pearl","year":"1997","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Balke, 1995] Alexander Balke. Probabilistic Counterfac- tuals: Semantics, Computation, and Applications. Ph.D. Thesis, University of California, Los Angeles, 1995.","title":"Probabilistic Counterfactuals: Semantics, Computation, and Applications","authors":"Alexander Balke","year":"1995","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai et al., 2007] Zhihong Cai, Manabu Kuroki, and Tosiya Sato. Non-parametric bounds on treatment effects with non-compliance by covariate adjustment. Statistics in Medicine, 26(16):3188-3204, 2007.","title":"Non-parametric bounds on treatment effects with non-compliance by covariate adjustment","authors":"Zhihong Cai, Manabu Kuroki, Tosiya Sato","year":"2007","venue":"Statistics in Medicine","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cai et al., 2008] Zhihong Cai, Manabu Kuroki, Judea Pearl, and Jin Tian. Bounds on direct effects in the pres- ence of confounded intermediate variables. Biometrics, 64(3):695-701, 2008.","title":"Bounds on direct effects in the presence of confounded intermediate variables","authors":"Zhihong Cai, Manabu Kuroki, Judea Pearl, Jin Tian","year":"2008","venue":"Biometrics","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cinelli and Hazlett, 2020] Carlos Cinelli and Chad Hazlett. Making sense of sensitivity: Extending omitted variable bias. Journal of the Royal Statistical Society Series B- Statistical Methodology, 82(1):39-67, 2020.","title":"Carlos Cinelli and Chad Hazlett. Making sense of sensitivity: Extending omitted variable bias","authors":"Hazlett Cinelli","year":"2020","venue":"Journal of the Royal Statistical Society Series B-Statistical Methodology","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Greenland, 2003] Sander Greenland. The impact of prior distributions for uncontrolled confounding and response bias: a case study of the relation of wire codes and mag- netic fields to childhood leukemia. Journal of the Ameri- can Statistical Association, 98(461):47-54, 2003.","title":"The impact of prior distributions for uncontrolled confounding and response bias: a case study of the relation of wire codes and magnetic fields to childhood leukemia","authors":"Sander Greenland","year":"2003","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Greenland, 2005] Sander Greenland. Multiple-bias mod- eling for analysis of observational data. Journal of the Royal Statistical Society: Series A (Statistics in Society), 168(2):267-306, 2005.","title":"Multiple-bias modeling for analysis of observational data","authors":"Sander Greenland","year":"2005","venue":"Journal of the Royal Statistical Society: Series A (Statistics in Society)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Imbens and Rubin, 2015] Guido W. Imbens and Donald B. Rubin. Causal Inference in Statistics, Social, and Biomed- ical Sciences. Cambridge University Press, 2015.","title":"Causal Inference in Statistics, Social, and Biomedical Sciences","authors":"Guido W Imbens, Donald B Rubin","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kuroki and Cai, 2008] Manabu Kuroki and Zhihong Cai. Formulating tightest bounds on causal effects in studies with unmeasured confounders. Statistics in Medicine, 27(30):6597-6611, 2008.","title":"Formulating tightest bounds on causal effects in studies with unmeasured confounders","authors":"Cai ; ] Manabu Kuroki, Zhihong Kuroki, Cai","year":"2008","venue":"Statistics in Medicine","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kuroki and Miyakawa, 2003] Manabu Kuroki and Masami Miyakawa. Covariate selection for estimating the causal effect of control plans by using causal diagrams. Jour- nal of the Royal Statistical Society: Series B (Statistical Methodology), 65(1):209-222, 2003.","title":"Covariate selection for estimating the causal effect of control plans by using causal diagrams","authors":"Miyakawa Kuroki, Manabu Kuroki, Masami Miyakawa","year":"2003","venue":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kuroki, 2008] Manabu Kuroki. The evaluation of causal ef- fects on the variance and its application to process anal- ysis. Journal of the Journal of The Japanese Society for Quality Control, 38:407-418, 2008.","title":"The evaluation of causal effects on the variance and its application to process analysis","authors":"Manabu Kuroki","year":"2008","venue":"Journal of the Journal of The Japanese Society for Quality Control","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kuroki, 2012] Manabu Kuroki. Optimizing a control plan using a structural equation model with an application to statistical process analysis. Journal of Applied Statistics, 39(3):673-694, 2012.","title":"Optimizing a control plan using a structural equation model with an application to statistical process analysis","authors":"Manabu Kuroki","year":"2012","venue":"Journal of Applied Statistics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2023] Ang Li, Scott Mueller, and Judea Pearl. ϵ- identifiability of causal quantities. Technical Report R- 525, <http://ftp.cs.ucla.edu/pub/stat ser/r525.pdf>, De- partment of Computer Science, University of California, Los Angeles, CA, 2023.","title":"ϵidentifiability of causal quantities","authors":"Ang Li, Scott Mueller, Judea Pearl","year":"2023","venue":null,"doi":null,"url":"<http://ftp.cs.ucla.edu/pub/statser/r525.pdf>,De-partmentofComputer","internal_url":null},{"position":14,"raw":"[MacLehose et al., 2005] Richard F MacLehose, Sol Kauf- man, Jay S Kaufman, and Charles Poole. Bounding causal effects under uncontrolled confounding using counterfac- tuals. Epidemiology, pages 548-555, 2005.","title":"Bounding causal effects under uncontrolled confounding using counterfactuals","authors":"Sol Richard F Maclehose, Jay S Kaufman, Charles Kaufman, Poole","year":"2005","venue":"Epidemiology","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Manski, 1990] Charles F Manski. Nonparametric bounds on treatment effects. The American Economic Review, 80(2):319-323, 1990.","title":"Nonparametric bounds on treatment effects","authors":"F Charles, Manski","year":"1990","venue":"The American Economic Review","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[McCandless et al., 2007] Lawrence C McCandless, Paul Gustafson, and Adrian Levy. Bayesian sensitivity anal- ysis for unmeasured confounding in observational studies. Statistics in Medicine, 26(11):2331-2347, 2007.","title":"Bayesian sensitivity analysis for unmeasured confounding in observational studies","authors":"Paul Lawrence C Mccandless, Adrian Gustafson, Levy","year":"2007","venue":"Statistics in Medicine","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[McCandless et al., 2008] Lawrence C McCandless, Paul Gustafson, and Adrian R Levy. A sensitivity analysis us- ing information about measured confounders yielded im- proved uncertainty assessments for unmeasured confound- ing. Journal of Clinical Epidemiology, 61(3):247-255, 2008.","title":"A sensitivity analysis using information about measured confounders yielded improved uncertainty assessments for unmeasured confounding","authors":"Paul Lawrence C Mccandless, Adrian R Gustafson, Levy","year":"2008","venue":"Journal of Clinical Epidemiology","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pearl, 2009] Judea Pearl. Causality: Models, Reasoning and Inference. Cambridge University Press, 2nd edition, 2009.","title":"Judea Pearl. Causality: Models, Reasoning and Inference","authors":"Pearl","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Peña, 2022] Jose M Peña. Simple yet sharp sensitivity anal- ysis for unmeasured confounding. Journal of Causal In- ference, 10(1):1-17, 2022.","title":"Simple yet sharp sensitivity analysis for unmeasured confounding","authors":"M Jose, Peña","year":"2022","venue":"Journal of Causal Inference","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tian and Pearl, 2000] Jin Tian and Judea Pearl. Probabil- ities of causation: Bounds and identification. Annals of Mathematics and Artificial Intelligence, 28(1-4):287-313, 2000.","title":"Probabilities of causation: Bounds and identification","authors":"Pearl ; Tian, Jin Tian, Judea Pearl","year":"2000","venue":"Annals of Mathematics and Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tian and Pearl, 2002] Jin Tian and Judea Pearl. A general identification condition for causal effects. In National Conference on Artificial Intelligence, volume 18, pages 567-573. AAAI Press, 2002.","title":"A general identification condition for causal effects","authors":"Pearl ; Tian, Jin Tian, Judea Pearl","year":"2002","venue":"National Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[VanderWeele and Ding, 2017] Tyler J VanderWeele and Peng Ding. Sensitivity analysis in observational research: introducing the e-value. Annals of Internal Medicine, 167(4):268-274, 2017.","title":"Sensitivity analysis in observational research: introducing the e-value","authors":"J Tyler, Peng Vanderweele, Ding","year":"2017","venue":"Annals of Internal Medicine","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[VanderWeele et al., 2019] Tyler J. VanderWeele, Peng Ding, and Maya Mathur. Technical considerations in the use of the e-value. Journal of Causal Inference, 7(2):20180007, 2019.","title":"Technical considerations in the use of the e-value","authors":"J Tyler, Peng Vanderweele, Maya Ding, Mathur","year":"2019","venue":"Journal of Causal Inference","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}