计量经济学第四第五章课后习题.doc

1) 存在=且=。
因为=,
当x2与x3之间的相关系数为零时,离差形式的=0,有
===
同理,=
2) 会
3) 存在Var()=Var()且Var()=Var()。
因为Var()=,
当=0时,
Var()===Var()
同理,Var()=Var()。

:
Dependent Variable: LNY
Method: Least Squares
Date: 05/16/12 Time: 19:34
Sample: 1985 2007
Included observations: 23
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
-

-

LNX1




LNX2
-

-

R-squared

Mean dependent var

Adjusted R-squared

. dependent var

. of regression

Akaike info criterion
-
Sum squared resid

Schwarz criterion
-
Log likelihood

F-statistic

Durbin-Watson stat

Prob(F-statistic)

建立如下模型:
lnYt=β1+β2lnGDPt +β3lnCPIt+ui

即:lnYt= - + lnGDPt +-+ui
() () ()
t =(-) () (-)
R2= = F= df=20
数据中有多重共线性,居民消费价格指数的回归系数的符号不能进行合理的经济意义解释,且其简单相关系数呈现正向变动。

Dependent Variable: LNY
Method: Least Squares
Date: 05/16/12 Time: 19:52
Sample: 1985 2007
Included observations: 23
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
-

-

LNX1




R-squared

Mean dependent var

Adjusted R-squared

. dependent var

. of regression

Akaike info criterion
-
Sum squared resid

Schwarz criterion
-
Log likelihood

F-statistic

Durbin-Watson stat

Prob(F-statistic)

lnYt= A1 + A2 lnGDPt + ui
= - + lnGDP
Se = ( ) ( )
R2 =, =
模型2
Dependent Variable: LNY
Method: Least Squares
Date: 05/16/12 Time: 19:58
Sample: 1985 2007
Included observations: 23
Variable
Coefficient
Std.