第一次发帖,有点激动。。。
有个问题希望得到好心人士的帮助。
使用stata在进行面板单位根ips检验时,加入滞后选项和不加入滞后选项即lags(#),为什么显示的结果统计量不一样,不加入lags(#)显示3个统计量,加入lags(#)显示一个统计量。有人知道差别在哪吗??谢谢了
xtunitroot ips lngdp,demean lags(aic 8)
Im-Pesaran-Shin unit-root test for lngdp
----------------------------------------
Ho: All panels contain unit roots Number of panels = 87
Ha: Some panels are stationary Number of periods = 12
AR parameter: Panel-specific Asymptotics: T,N -> Infinity
Panel means: Included sequentially
Time trend: Not included Cross-sectional means removed
ADF regressions: 0.00 lags average (chosen by AIC)
------------------------------------------------------------------------------
Statistic p-value
------------------------------------------------------------------------------
W-t-bar -10.9595 0.0000
------------------------------------------------------------------------------
xtunitroot ips lngdp,demean
Im-Pesaran-Shin unit-root test for lngdp
----------------------------------------
Ho: All panels contain unit roots Number of panels = 87
Ha: Some panels are stationary Number of periods = 12
AR parameter: Panel-specific Asymptotics: T,N -> Infinity
Panel means: Included sequentially
Time trend: Not included Cross-sectional means removed
ADF regressions: No lags included
------------------------------------------------------------------------------
Fixed-N exact critical values
Statistic p-value 1% 5% 10%
------------------------------------------------------------------------------
t-bar -2.6892 -1.740 -1.670 -1.640
t-tilde-bar -1.4343
Z-t-tilde-bar -1.6556 0.0489
------------------------------------------------------------------------------


雷达卡




京公网安备 11010802022788号







