表二 X:
ADF Test Statistic 1.222472 1% Critical Value* -4.1366
5% Critical Value -3.1483
10% Critical Value -2.7180
*MacKinnon critical values for rejection of hypothesis of a unit root.
Augmented Dickey-Fuller Test Equation
Dependent Variable: D(SER01)
Method: Least Squares
Date: 06/03/05 Time: 19:40
Sample(adjusted): 1993 2004
Included observations: 12 after adjusting endpoints
Variable Coefficient Std. Error t-Statistic Prob.
SER01(-1) 0.054515 0.044594 1.222472 0.2496
C 383.3354 254.7627 1.504677 0.1633
R-squared 0.130014 Mean dependent var 674.7475
Adjusted R-squared 0.043015 S.D. dependent var 318.2914
S.E. of regression 311.3704 Akaike info criterion 14.47086
Sum squared resid 969515.2 Schwarz criterion 14.55167
Log likelihood -84.82513 F-statistic 1.494438
Durbin-Watson stat 1.117371 Prob(F-statistic) 0.249560
/1.222472/</-4.1366/
/-3.1483/
/-2.7180/
拒绝原假设,没有通过检验,证明是不平稳的。
表三 Y:
ADF Test Statistic 2.333367 1% Critical Value* -4.1366
5% Critical Value -3.1483
10% Critical Value -2.7180
*MacKinnon critical values for rejection of hypothesis of a unit root.
Augmented Dickey-Fuller Test Equation
Dependent Variable: D(SER02)
Method: Least Squares
Date: 06/03/05 Time: 19:35
Sample(adjusted): 1993 2004
Included observations: 12 after adjusting endpoints
Variable Coefficient Std. Error t-Statistic Prob.
SER02(-1) 0.094160 0.040354 2.333367 0.0418
C 21.08984 8.483771 2.485904 0.0322
R-squared 0.352525 Mean dependent var 36.99833
Adjusted R-squared 0.287777 S.D. dependent var 20.72437
S.E. of regression 17.48998 Akaike info criterion 8.712145
Sum squared resid 3058.993 Schwarz criterion 8.792963
Log likelihood -50.27287 F-statistic 5.444602
Durbin-Watson stat 1.344857 Prob(F-statistic) 0.041810
/2.333367/</-4.1366/
/ -3.1483 /
/-2.7180/
拒绝原假设,没有通过检验,证明是不平稳的。
(二)进行协整性检验
生成ET=X-(α+ρ y)
表四
1992 2178.858
1993 2719.898
1994 3618.3
1995 4379.938
1996 4936.71
1997 5269.316
1998 5517.76
1999 5914.18
2000 6309.93
2001 6853.7
2002 8115.82
2003 8960.514
2004 10009.44
检验ET的平稳性
DW=0.462912
在显著性水平为0.05和0.1下通过水平型检验。
也就是说,我们要在以下的检验中用0.05和0.1的显著性水平对我们的数据进行估计和检验。
五.参数估计与检验
(一)将样本数据导入Eviews软件进行OLS估计,得到输出结果如下:
表五
Dependent Variable: SER02
Method: Least Squares
Date: 06/01/05 Time: 20:41
Sample: 1992 2004
Included observations: 13
Variable Coefficient Std. Error t-Statistic Prob.
SER01 0.060313 0.003423 17.62135 0.0000
C -153.6739 21.10424 -7.281659 0.0000
R-squared 0.965787 Mean dependent var 190.9238
Adjusted R-squared 0.962676 S.D. dependent var 148.0898
S.E. of regression 28.60996 Akaike info criterion 9.686025
Sum squared resid 9003.829 Schwarz criterion 9.772940
Log likelihood -60.95916 F-statistic 310.5121
Durbin-Watson stat 0.462912 Prob(F-statistic) 0.000000