天津商学院学报
天津商學院學報
천진상학원학보
JOURNAL OF TIANJIN UNIVERSITY OF COMMERCE
2002年
3期
5-7,14
,共4页
约束线性模型%两步约束最小二乘%伪变量
約束線性模型%兩步約束最小二乘%偽變量
약속선성모형%량보약속최소이승%위변량
restricted linear model%two step restricted least square%dummy variable
考虑线性变换对约束线性模型回归系数的影响问题.证明了观测数据的线性变换对于约束模型的影响可以通过一个可用两步约束最小二乘法解决的约束回归问题进行分析,得到了回归系数的约束可估函数的约束最佳线性无偏估计不受变换影响的充要条件.
攷慮線性變換對約束線性模型迴歸繫數的影響問題.證明瞭觀測數據的線性變換對于約束模型的影響可以通過一箇可用兩步約束最小二乘法解決的約束迴歸問題進行分析,得到瞭迴歸繫數的約束可估函數的約束最佳線性無偏估計不受變換影響的充要條件.
고필선성변환대약속선성모형회귀계수적영향문제.증명료관측수거적선성변환대우약속모형적영향가이통과일개가용량보약속최소이승법해결적약속회귀문제진행분석,득도료회귀계수적약속가고함수적약속최가선성무편고계불수변환영향적충요조건.
In this article we consider the influence of the regression coefficient the arbitrary rank restricted linear model based on linear transformations of the dependent variable. It is shown that the effect of the transformations may be analyzed through an associated restricted regression problem which is amenable to solution by two step restricted least squares. The necessary and sufficient condition in terms of arbitrary transformations is established for that there is a linear restricted estimable function of A′Y which is a restricted best linear unbiased estimation.