摘要
在运用 AHP方法解决多因素、多目标决策问题时 ,如何衡量互反矩阵的一致性一直是决策者们关心的课题。本文对目前为人们广泛使用的 C.R.衡量法提供了统计解释 ,同时也对 C.R.临界值 0 .
When applying AHP to make decision, decision makers always use C.R. to measure the consistency of a reciprocal matrix. If C.R. ≤10%, then the reciprocal matrix is thought to be consistent, otherwise it is refused. But does it make sense to use C.R., the ratio of the C.I. to an average C.I. (known as R.I.) computed from 500 n×n random reciprocal matrices, to examine the consistency?And why should the upper bound of C.R. be 10%?The purpose of this paper is to explain the statistical meaning of using the consistency index C.R. from the point of estimate error control. We also discuss the rationality to use the 10% cut off rule.
出处
《系统工程理论方法应用》
2001年第1期75-78,共4页
Systems Engineering Theory·Methodology·Applications
基金
国家自然科学基金资助项目 !(199710 15 )
