做面板误差修正模型结果解读

morehast

2586

收藏 2018-07-30

各位前辈，因论文需要，做面板误差修正模型时出现如下结果，怎么解读啊？长期关系中lnl在10%水平下不显著要不要处理？还有误差修正模型的误差修正项不显著如何处理？如果要让ec滞后一阶又该输入什么指令？
我目前输入的指令为：

复制代码

Pooled Mean Group Regression
(Estimate results saved as pmg)

Panel Variable (i): id                         Number of obs    =    450
Time Variable (t): year                      Number of groups =       30
                                             Obs per group: min =       15
                                                            avg =    15.0
                                                            max =       15

                                             Log Likelihood    =  1742.167
------------------------------------------------------------------------------
   D.lngdp |    Coef. Std. Err.    z P>|z|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
ec          |
      lnk | 19.45288 8.737572    2.23 0.026    2.327558 36.57821
      lnl | -1.04964 .6957126 -1.51 0.131 -2.413211 .3139318
      lnrm |  -1.835809 1.04447 -1.76 0.079 -3.882932 .2113151
-------------+----------------------------------------------------------------
SR          |
      ec |  -.0002825 .0063998 -0.04 0.965 -.0128259 .0122609
         |
   lngdp |
      D2. | .7141263 .0722247    9.89 0.000    .5725685    .855684
         |
      lnk |
      D1. | 2.214147 .4459381    4.97 0.000    1.340125    3.08817
      D2. | .4718401 .3006361    1.57 0.117 -.1173959 1.061076
         |
      lnl |
      D1. | .8726268 .4958555    1.76 0.078 -.0992321 1.844486
      D2. |  -.3799223 .2231549 -1.70 0.089    -.817298 .0574533
         |
      lnrm |
      D1. | .0596855 .0299349    1.99 0.046    .0010142 .1183568
      D2. |  -.0252519 .0126699 -1.99 0.046 -.0500844 -.0004194
         |
   _cons |  -.1441961 .9659887 -0.15 0.881 -2.037499 1.749107
------------------------------------------------------------------------------