dai-discoveringlinear-2003.pdf (180.2 kB)
Discovering linear causal model from incomplete data
conference contribution
posted on 2003-01-01, 00:00 authored by Gang LiGang Li, Honghua Dai, Yiqing TuOne common drawback in algorithms for learning Linear Causal Models is that they can not deal with incomplete data set. This is unfortunate since many real problems involve missing data or even hidden variable. In this paper, based on multiple imputation, we propose a three-step process to learn linear causal models from incomplete data set. Experimental results indicate that this algorithm is better than the single imputation method (EM algorithm) and the simple list deletion method, and for lower missing rate, this algorithm can even find models better than the results from the greedy learning algorithm MLGS working in a complete data set. In addition, the method is amenable to parallel or distributed processing, which is an important characteristic for data mining in large data sets.
History
Title of proceedings
InTech'03 : Proceedings of the Fourth International Conference on Intelligent Technologies 2003Event
International Conference on Intelligent Technologies (4th : 2003, Thailand)Pagination
1 - 11Publisher
Chiang Mai University, Institute for Science and Technology Research and DevelopmentLocation
Chiang Mai Plaza, ThailandPlace of publication
Chiang Mai, ThailandStart date
2003-12-17End date
2003-12-19ISBN-13
9789746581516ISBN-10
9746581511Language
engNotes
Every reasonable effort has been made to ensure that permission has been obtained for items included in Deakin Research Online. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.auPublication classification
E1 Full written paper - refereedCopyright notice
2003, InTechEditor/Contributor(s)
S DhompongsaUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC