Admissibility of linear estimate in a general variance components model 一般方差分量模型中線性估計的可容許性
As hurst parameter estimated bias exists , the precision may be improved by using non - linear estimate , where arfima model is proposed and used for verification 從統(tǒng)計結(jié)果來看,樣本序列呈現(xiàn)出尖峰、胖尾等有偏特征,明顯不滿足正態(tài)分布的假設(shè),表明收益序列可能具有長程相關(guān)或記憶性。
In this case optimally weighted ls estimate is not a linear estimate of a parameter given input and observation anymore and can not be compared with linear minimum variance estimate 在這種情況下,最優(yōu)加權(quán)最小二乘估計變成關(guān)于觀測和輸入的非線性估計,且與線性最小方差估計不可比。