麻烦弄一下面板协整的检验，主要是本人的软件每次做这个就出问题，谢谢了， [推广有奖]

21楼

billsgq

发表于 2011-3-27 10:34:29 |只看作者 |坛友微信交流群

Panel unit root test: Summary
Series:  WL
Date: 03/27/11 Time: 10:34
Sample: 1990 2000
Exogenous variables: Individual effects
User-specified lags: 1
and Bartlett kernel
Balanced observations for each test

Cross-
Method Statistic Prob.** sections Obs
Null: Unit root (assumes common unit root process)
Levin, Lin & Chu t*    5.33351    1.0000    31    279

Null: Unit root (assumes individual unit root process)
Im, Pesaran and Shin W-stat    8.50369    1.0000    31    279
ADF - Fisher Chi-square    5.36972    1.0000    31    279
PP - Fisher Chi-square    9.37649    1.0000    31    310

** Probabilities for Fisher tests are computed using an asymptotic Chi
      -square distribution. All other tests assume asymptotic normality.

使用道具举报

22楼

billsgq

发表于 2011-3-27 10:35:08 |只看作者 |坛友微信交流群

Panel unit root test: Summary
Series:  D(WL)
Date: 03/27/11 Time: 10:34
Sample: 1990 2000
Exogenous variables: Individual effects
Automatic selection of maximum lags
Automatic lag length selection based on SIC: 0 to 1
User-specified bandwidth: 1 and Bartlett kernel

Cross-
Method Statistic Prob.** sections Obs
Null: Unit root (assumes common unit root process)
Levin, Lin & Chu t* -27.8508    0.0000    31    276

Null: Unit root (assumes individual unit root process)
Im, Pesaran and Shin W-stat -16.8744    0.0000    31    276
ADF - Fisher Chi-square    336.331    0.0000    31    276
PP - Fisher Chi-square    383.582    0.0000    31    279

** Probabilities for Fisher tests are computed using an asymptotic Chi
      -square distribution. All other tests assume asymptotic normality.

使用道具举报

23楼

billsgq

发表于 2011-3-27 10:59:15 |只看作者 |坛友微信交流群

i.year          _Iyear_1990-2000 (naturally coded; _Iyear_1990 omitted)

Fixed-effects (within) regression             Number of obs    =    341
Group variable: id                            Number of groups =       31

R-sq:  within  = 0.9267                      Obs per group: min =       11
   between = 0.0065                                     avg =    11.0
   overall = 0.9030                                     max =       11

                                             F(11,299)       = 343.43
corr(u_i, Xb)  = -0.0061                      Prob > F          = 0.0000

------------------------------------------------------------------------------
      wl |    Coef. Std. Err.    t P>|t|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
      eco | .0596925 .0259115    2.30 0.022    .0087004 .1106845
_Iyear_1991 | .0644891 .0156126    4.13 0.000    .0337646 .0952137
_Iyear_1992 | .1267852 .016289    7.78 0.000    .0947295 .1588409
_Iyear_1993 | .0634368 .0175705    3.61 0.000    .0288594 .0980143
_Iyear_1994 | .2461901 .0197519 12.46 0.000    .2073199 .2850604
_Iyear_1995 | .137961 .0230811    5.98 0.000    .0925389    .183383
_Iyear_1996 | .2506963 .0278258    9.01 0.000    .1959371 .3054556
_Iyear_1997 | .2906138 .0334893    8.68 0.000    .2247092 .3565184
_Iyear_1998 | .4153979 .0405243 10.25 0.000    .335649 .4951469
_Iyear_1999 | .4609663 .0493424    9.34 0.000    .3638638 .5580687
_Iyear_2000 | .4941521 .0580439    8.51 0.000    .3799258 .6083784
   _cons | .1863813 .0111702 16.69 0.000    .1643992 .2083635
-------------+----------------------------------------------------------------
   sigma_u |  .03450025
   sigma_e |  .06074081
      rho |  .24392154 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0:    F(30, 299) =    3.50          Prob > F = 0.0000

.

使用道具举报

24楼

billsgq

发表于 2011-3-27 10:59:51 |只看作者 |坛友微信交流群

Random-effects GLS regression                Number of obs    =    341
Group variable: id                            Number of groups =       31

R-sq:  within  = 0.8635                      Obs per group: min =       11
   between = 0.0065                                     avg =    11.0
   overall = 0.8169                                     max =       11

Random effects u_i ~ Gaussian                Wald chi2(1)    = 1773.32
corr(u_i, X)    = 0 (assumed)             Prob > chi2       = 0.0000

------------------------------------------------------------------------------
      wl |    Coef. Std. Err.    z P>|z|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
      eco | .2733538 .0064913 42.11 0.000    .2606311 .2860765
   _cons | .2195372 .0088613 24.77 0.000    .2021694    .236905
-------------+----------------------------------------------------------------
   sigma_u |  .02444663
   sigma_e |  .08152657
      rho |  .08249857 (fraction of variance due to u_i)
------------------------------------------------------------------------------

.

使用道具举报

25楼

billsgq

发表于 2011-3-27 11:11:12 |只看作者 |坛友微信交流群

Arellano-Bond dynamic panel-data estimation  Number of obs       =    279
Group variable: id                         Number of groups    =       31
Time variable: year
                                          Obs per group: min =       9
                                                            avg =       9
                                                            max =       9

Number of instruments =    47             Wald chi2(2)       = 3164.52
                                          Prob > chi2          = 0.0000
One-step results
------------------------------------------------------------------------------
      wl |    Coef. Std. Err.    z P>|z|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
      wl |
      L1. |  -.5326837 .0641651 -8.30 0.000    -.658445 -.4069223
      eco | .3991696 .0167525 23.83 0.000    .3663354 .4320038
   _cons | .3314757 .0132639 24.99 0.000    .3054789 .3574725
------------------------------------------------------------------------------
Instruments for differenced equation
      GMM-type: L(2/.).wl
      Standard: D.eco
Instruments for level equation
      Standard: _cons

动态面板矩估计

使用道具举报