基于改进IDA算法的贝叶斯网络因果推断  

Causal inference of Bayesian network using improved IDA algorithm

作　　者：魏兵 徐平峰 WEI Bing;XU Ping-feng(School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China;Academy for Advanced Interdisciplinary Studies,Northeast Normal University,Changchun 130024,China)

机构地区：[1]长春工业大学数学与统计学院,吉林长春130012 [2]东北师范大学前沿交叉研究院,吉林长春130024

出　　处：《东北师大学报（自然科学版）》2023年第3期45-48,共4页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(11571050,11871013);吉林省自然科学基金资助项目(20210101152JC).

摘　　要：为了提高IDA估计的准确性,将估计DAG的PC算法换成基于自助法(Bootstrap)的贝叶斯网络结构学习算法即PCboot算法,然后与IDA算法的第二步内容结合起来.研究表明,在模拟研究和T细胞数据集上,新方法提高了IDA算法估计的准确性.In order to improve the accuracy of IDA algorithm,the PC algorithm for estimating DAG is replaced with the structural learning of Bayesian networks by Bootstrap,called PCboot algorithm,and then it is combined with the second step of IDA.Research shows that the new method improves the performance of IDA algorithm on both simulated and the T cell data set.

关 键 词：贝叶斯网络 自助法 PCboot算法 IDA算法 因果效应 

分 类 号：O21[理学—概率论与数理统计]