White Heteroskedasticity Test:   
   
F-statistic 3.254138     Probability  0.041380
Obs*R-squared 9.292044     Probability  0.054200
   
   
Test Equation:   
Dependent Variable: RESID^2   
Method: Least Squares   
Date: 12/08/10   Time: 11:25   
Sample: 1990 2009   
Included observations: 20   
   
Variable Coefficient Std. Error t-Statistic Prob.  
   
C 1917313. 1085936. 1.765586 0.0978
CZZC 40.58686 246.7936 0.164457 0.8716
CZZC^2 -0.003228 0.002321 -1.390839 0.1846
GDP -39.45270 48.37020 -0.815641 0.4275
GDP^2 0.000257 0.000122 2.112200 0.0519
   
R-squared 0.464602     Mean dependent var  1200617.
Adjusted R-squared 0.321829     S.D. dependent var  1771876.
S.E. of regression 1459160.     Akaike info criterion  31.43694
Sum squared resid 3.19E+13     Schwarz criterion  31.68587
Log likelihood -309.3694     F-statistic  3.254138
Durbin-Watson stat 3.011491     Prob(F-statistic)  0.041380
   




还有就是我用wls之后结果自变量变得不能接受了，这个有没有关系的？
Sample: 1990 2009   
Included observations: 20   
Weighting series: WI   
   
Variable Coefficient Std. Error t-Statistic Prob.  
   
C -64.24524 459.1566 -0.139920    0.8904
GDP 0.011654 0.020957 0.556076 0.5854
CZZC 0.790562 0.101126 7.817561 0.0000
   
Weighted Statistics   
   
R-squared 0.999896     Mean dependent var  18261.44
Adjusted R-squared 0.999884     S.D. dependent var  34444.92
S.E. of regression 370.5648     Akaike info criterion  14.80541
Sum squared resid 2334411.     Schwarz criterion  14.95477
Log likelihood -145.0541     F-statistic  82073.06
Durbin-Watson stat 1.739994     Prob(F-statistic)  0.000000
   
Unweighted Statistics   
   
R-squared 0.993789     Mean dependent var  18613.20
Adjusted R-squared 0.993058     S.D. dependent var  17451.18
S.E. of regression 1453.994     Sum squared resid  35939684
Durbin-Watson stat 1.241115