word专业整理
1,000,000,000800,000,000600,000,000EI2400,000,000200,000,000040,00050,00060,000X170,00080,000 图4：初始模型的异方差性检验散点图
1,000,000,000800,000,000600,000,000EI2400,000,000200,000,0000050,000100,000150,000200,000250,000X2 图5：初始模型的异方差性检验散点图
1,000,000,000800,000,000600,000,000EI2400,000,000200,000,000095100105110X3115120125 图6：初始模型的异方差性检验散点图
学习资料 整理分享
word专业整理
通过图形看到，回归线向上倾斜，大致判断存在异方差性，但是，图示法并不准确，下面使用White异方差检验法进行检验，分别选择不带有交叉项和带有交叉项的White异方差检验法。得到下面的检验结果：
表5：不带有交叉项的White异方差检验结果
Heteroskedasticity Test: White
F-statistic Obs*R-squared Scaled explained SS
Test Equation:
Dependent Variable: RESID^2 Method: Least Squares Date: 5/25/16 Time: 9:15 Sample: 1980 2009 Included observations: 30
C X1^2 X2^2 X3^2
R-squared
Coefficien
t
1.51E+08 -0.029775 0.017419 -2715.996
Std. Error
1.08E+08 0.009593 0.001245 8243.375
75.59849 Prob. F(3,26) 26.91450 Prob. Chi-Square(3) 52.75104 Prob. Chi-Square(3)
0.0000 0.0000 0.0000
t-Statistic Prob.
1.398492 -3.103868 13.98776 -0.329476
0.1738 0.0046 0.0000 0.7444
77607780 1.80E+08 38.81668 39.00351 38.87645 1.947056
0.897150 Mean dependent var 0.885283 S.D. dependent var
Akaike info
61075426 criterion
9.70E+16 Schwarz criterion
Hannan-Quinn
-578.2502 criter.
75.59849 Durbin-Watson stat 0.000000
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic)
表6：带有交叉项的White异方差检验结果
Heteroskedasticity Test: White
F-statistic Obs*R-squared Scaled explained SS
学习资料 整理分享
33.57944 Prob. F(9,20) 28.13789 Prob. Chi-Square(9) 55.14882 Prob. Chi-Square(9)
0.0000 0.0009 0.0000
word专业整理
Test Equation:
Dependent Variable: RESID^2 Method: Least Squares Date: 5/25/16 Time: 9:18 Sample: 1980 2009 Included observations: 30
C X1 X1^2 X1*X2 X1*X3 X2 X2^2 X2*X3 X3 X3^2
R-squared
Coefficien
t
-2.08E+09 -34576.99 0.189719 -0.297299 127.5161 29147.14 0.033135 -97.11637 55473498 -283697.5
Std. Error
4.06E+09 39720.32 0.224091 0.442472 329.2824 35662.29 0.007760 96.87489 68538734 290382.6
t-Statistic Prob.
-0.512912 -0.870512 0.846615 -0.671906 0.387254 0.817310 4.270053 -1.002493 0.809374 -0.976978
0.6136 0.3943 0.4072 0.5093 0.7027 0.4234 0.0004 0.3281 0.4278 0.3403
77607780 1.80E+08 38.71168 39.17875 38.86110 2.262413
0.937930 Mean dependent var 0.909998 S.D. dependent var
Akaike info
54097636 criterion
5.85E+16 Schwarz criterion
Hannan-Quinn
-570.6752 criter.
33.57944 Durbin-Watson stat 0.000000
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic)
使用White检验法不论是否带有交叉项，所得的检验伴随概率均小于5%，均在5%的显著水平下拒绝方程不存在异方差性的原假设，认为模型具有比较严重的异方差性。需要对模型进行修正。
②多重共线性检验： 用逐步回归法检验如下
以?为被解释变量，逐个引入解释变量?1、?2、?3，构成回归模型，进行模型估计。
表7： 被解释变量?与?1最小二乘估计结果
学习资料 整理分享
word专业整理
Dependent Variable: Y Method: Least Squares Date: 5/25/16 Time: 9:20 Sample: 1980 2009 Included observations: 30
X1 C
R-squared
Coefficien
t
6.692086 -334986.1
Std. Error
0.880526 56283.70
t-Statistic Prob.
7.600101 -5.951743
0.0000 0.0000
85749.31 95692.85 24.75574 24.84915 24.78562 0.096883
0.673513 Mean dependent var 0.661853 S.D. dependent var
Akaike info
55645.78 criterion
8.67E+10 Schwarz criterion
Hannan-Quinn
-369.3361 criter.
57.76153 Durbin-Watson stat 0.000000
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic)
表8： 被解释变量?与?2最小二乘估计结果
Dependent Variable: Y Method: Least Squares Date: 5/25/16 Time: 9:21 Sample: 1980 2009 Included observations: 30
X2 C
R-squared
Coefficien
t
1.688594 19746.45
Std. Error
0.063011 4234.328
t-Statistic Prob.
26.79831 4.663420
0.0000 0.0001
85749.31 95692.85 22.59239 22.68580 22.62227 0.402624
0.962474 Mean dependent var 0.961134 S.D. dependent var
Akaike info
18865.38 criterion
9.97E+09 Schwarz criterion
Hannan-Quinn
-336.8858 criter.
718.1495 Durbin-Watson stat 0.000000
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic)
学习资料 整理分享
word专业整理
表9： 被解释变量?与?3最小二乘估计结果
Dependent Variable: Y Method: Least Squares Date: 5/25/16 Time: 9:25 Sample: 1980 2009 Included observations: 30
X3 C
R-squared
Coefficien
t
-4733.789 586426.4
Std. Error
2602.669 275788.7
t-Statistic Prob.
-1.818821 2.126361
0.0797 0.0424
85749.31 95692.85 25.76343 25.85685 25.79332 0.120717
0.105663 Mean dependent var 0.073722 S.D. dependent var
Akaike info
92097.98 criterion
2.37E+11 Schwarz criterion
Hannan-Quinn
-384.4515 criter.
3.308109 Durbin-Watson stat 0.079650
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic)
由图可以看出，?与?2的拟合优度是最大的，R-squared=0.962474。再做?与?1和?2的回归模型。
表10： 被解释变量?与?1和?2的最小二乘估计结果
Dependent Variable: Y Method: Least Squares Date: 5/25/16 Time: 9:28 Sample: 1980 2009 Included observations: 30
X1 X2 C
R-squared
Coefficien
t
1.963607 1.391253 -92084.42
Std. Error
0.218188 0.046055 12611.85
t-Statistic Prob.
8.999617 30.20878 -7.301423
0.0000 0.0000 0.0000
85749.31
0.990618 Mean dependent var
学习资料 整理分享
中国经济增长影响因素的分析报告书
