回归及Hauman 检验

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

请高手帮我看下，我的数据是面板数据，这样的hausman 检验后能用固定模型吗，我这样最后得到的回归结果能用吗，如果其中某个变量不显著，一定得删除吗

还有就是想回归时显示调整R平方怎么办呢，我用的是

 xtreg var1 var2 var3, fe

  Hausman 检验---- Coefficients ----
             |      (b)          (B)            (b-B)     sqrt(diag(V_b-V_B))
             |       fe           re         Difference          S.E.
-------------+----------------------------------------------------------------
         var1 |   -.132524    -.1900192        .0517668        .0284982
       var2 |    .0414575      .009875           .0318818        .0028363
       var3 |    .3210128     .3310197       -.0230069              .
         ------------------------------------------------------------------------------
                           b = consistent under Ho and Ha; obtained from xtreg
            B = inconsistent under Ha, efficient under Ho; obtained from xtreg

    Test:  Ho:  difference in coefficients not systematic

                  chi2(6) = (b-B)'[(V_b-V_B)^(-1)](b-B)
                          =       49.75
                Prob>chi2 =      0.0000
                (V_b-V_B is not positive definite)

固定模型回归结果

Fixed-effects (within) regression               Number of obs      =      1062
Group variable: company                         Number of groups   =        82

R-sq:  within  = 0.4326                         Obs per group: min =         8
       between = 0.5443                                        avg =      13.0
       overall = 0.4349                                        max =        14

                                                F(6,974)           =     90.86
corr(u_i, Xb)  = -0.4908                        Prob > F           =    0.0000

                                (Std. Err. adjusted for clustering on company)
------------------------------------------------------------------------------
             |               Robust
         dis |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         var1 | -.132524    .0519624    -3.05   0.002    -.2602236   -.0562813
          var2|   0414575 .0289725    12.70   0.000     .3111571    .42486850414575      
          var3|  .3210128      02897254.84   0.000     .0102984    .0243407
              _cons |   .6021928   .0347549    17.33   0.000     .5339896    .6703959
-------------+----------------------------------------------------------------
     sigma_u |   .0949388
     sigma_e |  .12915659
         rho |  .35078596   (fraction of variance due to u_i)
------------------------------------------------------------------------------

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Hauman Man coefficients fixed-effect coefficient 检验 Hauman

以下是引用naoren2002在2009-5-31 22:42:00的发言：还有就是想回归时显示调整R平方怎么办呢

*回归后，使用

di e(r2_a)

https://bbs.pinggu.org/thread-272681-1-1.html

https://bbs.pinggu.org/thread-188722-1-1.html