【作者】 陆余楚； 金萍； 张立；

【Author】 LU Yu-chu, JIN Ping, ZHANG Li(Department of Mathematics, Shanghai University, Shanghai 200436, China; Institute of Mathematics, Fudan University, Shanghai 200433, China)

【机构】 上海大学数学系； 复旦大学数学研究所；

【摘要】 在进行风险分析与评估的过程中,总要涉及到对各类数据的处理和分析,而在许多情况下,能采集到的数据非常少,导致了信息量的不足,这就是所谓的小样本情况,本文对一实际课题,首先利用无限信息扩散方法对小样本问题进行处理,取得了较好的结果,在此基础上,根据优化原理,解决了扩散函数中的参数优化问题,取得了更为理想的结果。更多还原

【Abstract】 In the process of risk analysis and evaluation, it is necessary to collect, refine and analyze variety of data named information. But in some cases, the collectable data is rather scarce which results in the insufficient information.It is what you call"Small Sample Problem". In this paper, we first deal with the "Small sample problem" by the unlimited information diffusion method and get a preferable outcome. And then, the optimization problem of the parameter in the diffusion function is solved based on the optimization principles and an even better result is achieved.更多还原