基于Bootstrap的反舰导弹靶场试验小样本数据分析方法研究  

Data Analysis of Anti-ship Missile in Range Trial Small Sample Based on Bootstrap Method

作　　者：孙锦[1] 李国林[2] 许诚[3] 谢朝晖[4] 

机构地区：[1]海军航空工程学院研究生管理大队 [2]海军航空工程学院战略导弹工程系 [3]海军航空工程学院飞行器工程系 [4]75752部队

出　　处：《计算机与数字工程》2014年第1期48-51,共4页Computer & Digital Engineering

基　　金：国家部委重点资助项目(编号:2010214019)资助

摘　　要：自助法(Bootstrap)和随机加权法(Bayes Bootstrap)都能较好地处理小样本数据,其无先验性,以及计算过程中只需要实际观测数据的优越性,使其广泛地应用于实际数据处理之中,后者的估计精度要更好些。但对连续情况而言,自助法的计算特性使得重抽样本局限在原始样本范围内,无法渐进于真实情况。文章基于自助法研究了用改进的样本经验分布函数来解决这个问题,并通过仿真算例说明方法的有效性。Bootstrap method and Bayes Bootstrap method are all good methods to deal with the data of small sample,which are only dependent on the observation nather than other assumptior.Therefore,they are widely adopted,and the latter has higher precise.But as to the continuous function,the calculatingly characteristic of the Bootstrap method limits the range of the resample to the original data,so it will make the Bootstrap distribution departure from the genuine distribution.Therefore the improving empirical distruction function of sample is introduced to solve the problem,which is based on Bootstrap method.The emulation of example from the thesis proves the validity of the improving method.

关 键 词：靶场试验 小样本 参数估计 自助法 随机加权法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]