摘要
根据多种指标对事物的影响,从而对事物的属性进行判别分类,这是实际科研领域中经常要解决的问题。解决这些问题的方法有多种,最大似然判别法就是其中行之有效的方法之一。它的基本作法是:事先确定好影响所论事物属性的m个指标,以及已确定类别的N个历史样本。
In this paper a simple and efficient algorithm is presented. By using it we can easilyselect factor combination with the highest discriminating conformable rate of 2~m-1 combina-tions of the m factors in the procedure of using 'maximum likelihood discriminating method'(MLDM). The results of practical examples using the algorithm in this paper show that thealgorithm is not only simple and feasible but also very efficient. At the same time, the amountof its calculation is very small.
出处
《数值计算与计算机应用》
CSCD
北大核心
1990年第3期171-177,共7页
Journal on Numerical Methods and Computer Applications