Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

The role of assumptions in causal discovery

Druzdzel, Marek J. (2009) The role of assumptions in causal discovery. In: 8th Workshop on Uncertainty Processing (WUPES-09), 19 September 2009 - 23 September 2009, Liblice, Czech Republic.

[img]
Preview
PDF
Available under License : See the attached license file.

Download (181kB) | Preview
[img] Plain Text (licence)
Available under License : See the attached license file.

Download (1kB)

Abstract

The paper looks at the conditional independence search approach to causal discovery, proposed by Spirtes et al. and Pearl and Verma, from the point of view of the mechanism-based view of causality in econometrics, explicated by Simon. As demonstrated by Simon, the problem of determining the causal structure from data is severely underconstrained and the perceived causal structure depends on the a priori assumptions that one is willing to make. I discuss the assumptions made in the independence search-based causal discovery and their identifying strength.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Paper)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Druzdzel, Marek J.marek@sis.pitt.eduDRUZDZEL0000-0002-7598-2286
Date: September 2009
Date Type: Publication
Page Range: 57 - 68
Event Title: 8th Workshop on Uncertainty Processing (WUPES-09)
Event Dates: 19 September 2009 - 23 September 2009
Event Type: Conference
Institution: University of Pittsburgh
Schools and Programs: School of Information Sciences > Information Science
Refereed: Yes
Date Deposited: 13 Jul 2011 13:52
Last Modified: 05 Mar 2019 01:55
URI: http://d-scholarship.pitt.edu/id/eprint/6017

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item