基于基元前景交叉判断的前景价值模型

发布时间：2018-07-31 13:15

【摘要】：针对现有概率权重非参数确定方法存在的两方面缺陷,即因假设概率权重仅与概率有关而没有考虑概率权重受概率与结果共同影响的问题和没有针对决策者主观判断不准确性予以判断偏差有效控制的问题,通过引入两两比较思维构建了反映概率和结果对概率权重复杂影响的基元前景两两比较交叉判断新模式,并在此基础上运用误差控制优化技术提出了基元前景价值确定模型和前景优劣排序模型.数值模拟分析结果表明,应用前景优劣排序模型得到的前景排序与"假定能够事先知道、能够真实反映决策者在有限理性下实际选择行为"的真实排序具有高度一致性,证实了其克服现有非参数法固有缺陷的有效性.
[Abstract]:In view of the two defects of the existing non-parametric methods for determining probability weights, That is, the assumption that the probability weight is only related to probability without considering that the probability weight is influenced by both probability and result, and the problem that the judgment deviation is not effectively controlled against the inaccuracy of the subjective judgment of the decision maker. By introducing pairwise comparative thinking, a new model of comparative cross-judgement of the foreground of primitive elements, which reflects the complex influence of probability and result on probability weight, is constructed. On this basis, the model of determining the foreground value of the primitive and the ranking model of the foreground are put forward by using the error control optimization technique. The numerical simulation results show that there is a high degree of consistency between the foreground ranking obtained by using the foreground ranking model and the "assuming that the decision makers can know in advance and can truly reflect the actual choice behavior of the decision makers under finite rationality". It is proved that it is effective to overcome the inherent defects of the existing nonparametric methods.
【作者单位】：吉林大学管理学院;
【基金】：国家自然科学基金重点资助项目(70732005) 国家自然科学基金资助项目(7097105470471015) 教育部人文社会科学研究规划资助项目(09YJA630047) 吉林省软科学研究资助项目(20080610) 吉林大学‘211’工程资助项目吉林大学基本科研业务费资助项目(2008JC012)
【分类号】：C934;F224

【参考文献】