高人解答：stata做面板数据固定效应与随机效应的一个问题 [推广有奖]

21楼

number22 发表于 2010-3-1 00:29:01

20# sungmoo
非常感谢！！！真是麻烦版主了

22楼

蓝色 发表于 2010-3-1 08:32:02

number22 发表于 2010-2-28 18:36
13# 蓝色

版主你看为什么这三个不同命令主要结果一样，只是地区虚拟变量那不同？
xtset district year
   panel variable:  district (strongly balanced)
      time variable:  year, 1 to 5
            delta:  1 unit
.
xtreg var8 ti var4 a b,fe
Fixed-effects (within) regression             Number of obs    =    660
Group variable: district                      Number of groups =    132
R-sq:  within  = 0.5911                      Obs per group: min =       5
   between = 0.7004                                     avg =    5.0
   overall = 0.6042                                     max =       5
                                             F(4,524)          = 189.37
corr(u_i, Xb)  = 0.3915                      Prob > F          = 0.0000
------------------------------------------------------------------------------
      var8 |     Coef. Std. Err.    t P>|t|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
      ti |  -242.4167 19.49112 -12.44 0.000    -280.707 -204.1263
      var4 | 81.53912 24.10555    3.38 0.001    34.18373 128.8945
         a | .0333506 .0027825 11.99 0.000    .0278843 .0388168
         b | .015245 .0025494    5.98 0.000    .0102367 .0202532
   _cons | 197.9695 6.647092 29.78 0.000    184.9112 211.0277
-------------+----------------------------------------------------------------
   sigma_u |  159.92436
   sigma_e |  108.00245
      rho |  .68677695 (fraction of variance due to u_i)
------------------------------------------------------------------------------

. xi:xtreg var8 ti var4 a b i.district,fe
i.district       _Idistrict_1-132 (naturally coded; _Idistrict_1 omitted)
Fixed-effects (within) regression             Number of obs    =    660
Group variable: district                      Number of groups =    132
R-sq:  within  = 0.5911                      Obs per group: min =       5
   between = 0.7004                                     avg =    5.0
   overall = 0.6042                                     max =       5
                                             F(4,524)          = 189.37
corr(u_i, Xb)  = 0.3915                      Prob > F          = 0.0000
------------------------------------------------------------------------------
      var8 |     Coef. Std. Err.    t P>|t|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
      ti |  -242.4167 19.49112 -12.44 0.000    -280.707 -204.1263
      var4 | 81.53912 24.10555    3.38 0.001    34.18373 128.8945
         a | .0333506 .0027825 11.99 0.000    .0278843 .0388168
         b | .015245 .0025494    5.98 0.000    .0102367 .0202532
_Idistrict_2 |  (dropped)
_Idistrict_3 |  (dropped)
_Idistrict_4 |  (dropped)
_Idistrict_5 |  (dropped)
_Idistrict_6 |  (dropped)
_Idistrict_7 |  (dropped)
_Idistrict_8 |  (dropped)
--more--

. xi:xtreg var8 ti var4 a b i.district,re
i.district       _Idistrict_1-132 (naturally coded; _Idistrict_1 omitted)
Random-effects GLS regression                Number of obs    =    660
Group variable: district                      Number of groups =    132
R-sq:  within  = 0.5911                      Obs per group: min =       5
   between = 1.0000                                     avg =    5.0
   overall = 0.8808                                     max =       5
Random effects u_i ~ Gaussian                Wald chi2(135)    = 3871.97
corr(u_i, X)    = 0 (assumed)             Prob > chi2       = 0.0000
------------------------------------------------------------------------------
      var8 |    Coef. Std. Err.    z P>|z|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
      ti |  -242.4167 19.49112 -12.44 0.000 -280.6185 -204.2148
      var4 | 81.53912 24.10555    3.38 0.001    34.29311 128.7851
         a | .0333506 .0027825 11.99 0.000    .027897 .0388041
         b | .015245 .0025494    5.98 0.000    .0102483 .0202416
_Idistrict_2 | 17.75247 68.3175    0.26 0.795 -116.1474 151.6523
_Idistrict_3 | 51.38357 69.76842    0.74 0.461 -85.36002 188.1272
_Idistrict_4 | 164.425 68.77937    2.39 0.017    29.61995 299.2301
_Idistrict_5 | 45.44195 69.73088    0.65 0.515 -91.22807    182.112
_Idistrict_6 | 25.87626 69.72691    0.37 0.711    -110.786 162.5385
_Idistrict_7 |  -7.751544 69.92745 -0.11 0.912 -144.8068 129.3037
_Idistrict_8 | 94.96308 69.89578    1.36 0.174 -42.03012 231.9563

你的这些结果我这里允许不出来