这是我在一个模型中进行的滞后阶数判断
VAR Lag Order Selection Criteria
Endogenous variables: LNRHNI LNBEOA LNLTAS
Exogenous variables: C
Date: 01/12/11 Time: 17:10
Sample: 1978 2006
Included observations: 23
Lag LogL LR FPE AIC SC HQ
0 -4.760237 NA 0.000394 0.674803 0.822911 0.712052
1 59.01115 105.3614* 3.40e-06* -4.087926 -3.495495* -3.938931
2 62.16419 4.386829 5.94e-06 -3.579494 -2.542739 -3.318753
3 70.39839 9.308224 7.21e-06 -3.512903 -2.031824 -3.140416
4 81.42904 9.591872 7.88e-06 -3.689482 -1.764078 -3.205248
5 86.73521 3.229844 1.84e-05 -3.368279 -0.998552 -2.772299
6 121.4959 12.09068 6.00e-06 -5.608340* -2.794289 -4.900614*
* 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
AIC准则显示滞后6期,SC准则显示滞后1期,LR显示滞后1期(没错吧?),那么我建立VAR模型的最佳滞后期应该选择多少期呢?非常感谢。
我已经检测出变量在SC准则下是一阶差分平稳的。



雷达卡





京公网安备 11010802022788号







