非均方准则函数下增长率预测  

A prediction of growth rate by non-mean-square error criterion functions

作　　者：宋立新[1] 赵越[1] 冯敬海[1] 黄晓薇[2] 

机构地区：[1]大连理工大学应用数学系,辽宁大连116024 [2]对外经济贸易大学金融学院,北京100029

出　　处：《大连理工大学学报》2008年第3期465-468,共4页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(10271049)

摘　　要：资产组合的远期收益常为资本持有者及经济学研究人员所关注,在众多影响因素中,资本市场上外汇、股票、期货等交易较大地依赖于该资产未来的增长率,为此研究了收益率为未知时资产组合预期增长率预测值与真实值的极限比变化趋势.分别在对称熵准则函数和Linex准则函数下得出了最优预测值,进一步研究了在这两个准则条件下,实际增长率为独立同分布情况时估计值与真实值之比的极限情形,在大样本情形下讨论了风险水平与二者比值的关系,并经过真实数据模拟验证了所得结论.The future return o holders. Among many growth rate of the port growth rate compared portfolio are uncertain. factors folios in with The f portfolios usually attracts the attention of the bargains of exchange, stock and futures the future. The limiting behavior of the trend real development is considered when the pa economists and capital largely depend on the of the valuation of the yoffs of an investment best prediction value is given by criterions of the symmetric entropy criterion function and Linex criterion function. Then of the valuation to the real one is given for independen sample, and a simulation is built using true data to veri e relation between the risk level and the ratio t identically distributed growth rates in large fy the conclusions.

关 键 词：增长率 对称熵准则函数 Linex准则函数 JENSEN不等式 

分 类 号：O211[理学—概率论与数理统计]