2# nlm0402
第一个的回归结果
Dependent Variable: LNER
Method: Least Squares
Date: 09/01/09 Time: 15:12
Sample: 1 942
Included observations: 942
Variable Coefficient Std. Error t-Statistic Prob.
C 6.259970 0.137137 45.64748 0.0000
LNHK 0.141906 0.030037 4.724426 0.0000
R-squared 0.023194 Mean dependent var 6.907794
Adjusted R-squared 0.022155 S.D. dependent var 0.062806
S.E. of regression 0.062107 Akaike info criterion -2.717811
Sum squared resid 3.625786 Schwarz criterion -2.707518
Log likelihood 1282.089 Hannan-Quinn criter. -2.713887
F-statistic 22.32020 Durbin-Watson stat 0.012838
Prob(F-statistic) 0.000003
那个滞后阶数我是用VAR模型,找的Lag Length Criteria:
VAR Lag Order Selection Criteria
Endogenous variables: LNER LNHK
Exogenous variables: C
Date: 09/01/09 Time: 22:15
Sample: 1 942
Included observations: 934
Lag LogL LR FPE AIC SC HQ
0 2464.694 NA 1.76e-05 -5.273434 -5.263071 -5.269482
1 8601.917 12235.02 3.48e-11 -18.40668 -18.37559* -18.39482*
2 8604.297 4.734400 3.49e-11 -18.40321 -18.35139 -18.38345
3 8610.868 13.04362* 3.47e-11* -18.40871* -18.33617 -18.38105
4 8614.364 6.922953 3.47e-11 -18.40763 -18.31436 -18.37207
5 8616.988 5.186530 3.48e-11 -18.40468 -18.29069 -18.36122
6 8619.054 4.075771 3.50e-11 -18.40054 -18.26583 -18.34917
7 8620.630 3.100327 3.52e-11 -18.39535 -18.23991 -18.33608
8 8621.438 1.586022 3.54e-11 -18.38852 -18.21235 -18.32134
* indicates lag order selected by the criterion
LR: sequential modified LR test statistic (each test at 5% level)
FPE: Final prediction error
AIC: Akaike information criterion
SC: Schwarz information criterion
HQ: Hannan-Quinn information criterion
确定是 VAR(3)
所以在协整检验时滞后lag intervals 填的 1 2