A simple constraint-based algorithm for efficiently mining observational databases for causal relationships

被引:111
作者
Cooper, GF [1 ]
机构
[1] Univ Pittsburgh, Ctr Biomed Informat, Pittsburgh, PA 15213 USA
基金
美国国家科学基金会;
关键词
causal discovery; data mining; observational data;
D O I
10.1023/A:1009787925236
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a simple, efficient computer-based method for discovering causal relationships from databases that contain observational data. Observational data is passively observed, as contrasted with experimental data. Most of the databases available for data mining are observational. There is great potential for mining such databases to discover causal relationships. We illustrate how observational data can constrain the causal relationships among measured variables, sometimes to the point that we can conclude that one variable is causing another variable. The presentation here is based on a constraint-based approach to causal discovery. A primary purpose of this paper is to present the constraint-based causal discovery method in the simplest possible fashion in order to (1) readily convey the basic ideas that underlie more complex constraint-based causal discovery techniques, and (2) permit interested readers to rapidly program and apply the method to their own databases, as a start toward using more elaborate causal discovery algorithms.
引用
收藏
页码:203 / 224
页数:22
相关论文
共 23 条
[1]  
ALIFERIS C, 1994, P 10 C UNC ART INT S, P8
[2]  
ALMOND RG, 1997, WEB PAGE SOFTWARE LE
[3]  
[Anonymous], P 11 C UNC ART INT
[4]  
Bishop M.M., 1975, DISCRETE MULTIVARIAT
[5]  
BOUCKAERT RR, 1995, THESIS U UTRECHT UTR
[6]  
Castillo E., 1997, Expert Systems and Probabilistic Network Models
[7]  
Cooper G, 1995, P 5 INT WORKSH ART I, P140
[8]   A BAYESIAN METHOD FOR THE INDUCTION OF PROBABILISTIC NETWORKS FROM DATA [J].
COOPER, GF ;
HERSKOVITS, E .
MACHINE LEARNING, 1992, 9 (04) :309-347
[9]   IDENTIFYING INDEPENDENCE IN BAYESIAN NETWORKS [J].
GEIGER, D ;
VERMA, T ;
PEARL, J .
NETWORKS, 1990, 20 (05) :507-534
[10]  
HECKERMAN D, 1995, MACH LEARN, V20, P197, DOI 10.1007/BF00994016