Causal Subgroup Analysis for Detecting Confounding
This paper presents a causal subgroup analysis approach for the detection of confounding: We show how to identify (causal) relations between subgroups by generating an extended causal subgroup network utilizing background knowledge. Using the links within the network we can identify relations that are potentially confounded by external (confounding) factors. In a semi-automatic approach, the network and the discovered relations are then presented to the user as an intuitive visualization. The applicability and benefit of the presented technique is illustrated by examples from a case-study in the medical domain.
Unable to display preview. Download preview PDF.
- 2.Klösgen, W.: 16.3: Subgroup Discovery. In: Handbook of Data Mining and Knowledge Discovery. Oxford University Press, New York (2002)Google Scholar
- 7.Simpson, E.H.: The Interpretation of Interaction in Contingency Tables. Journal of the Royal Statistical Society 18, 238–241 (1951)Google Scholar
- 8.Fabris, C.C., Freitas, A.A.: Discovering Surprising Patterns by Detecting Occurrences of Simpson’s Paradox. In: Research and Development in Intelligent Systems XVI, pp. 148–160. Springer, Heidelberg (1999)Google Scholar
- 9.Pearl, J.: 6.2 Why There is No Statistical Test For Confounding, Why Many Think There Is, and Why They Are Almost Right. In: Causality: Models, Reasoning and Inference, Cambridge University Press, Cambridge (2000)Google Scholar
- 11.Atzmueller, M., Puppe, F., Buscher, H.P.: Exploiting Background Knowledge for Knowledge-Intensive Subgroup Discovery. In: Proc. 19th Intl. Joint Conference on Artificial Intelligence (IJCAI 2005), Edinburgh, Scotland, pp. 647–652 (2005)Google Scholar
- 12.Kloesgen, W., May, M.: Database Integration of Multirelational Causal Subgroup Mining. Technical report, Fraunhofer Institute AIS, Sankt Augustin, Germany (2002)Google Scholar
- 14.Atzmueller, M., Puppe, F.: Semi-Automatic Visual Subgroup Mining using VIKAMINE. Journal of Universal Computer Science 11(11), 1752–1765 (2005)Google Scholar