悬赏 30 个论坛币 未解决
我在做豪斯曼检验时候最后做出来结果不显著,应该用随机效应模型,但是看文献都用固定效应模型,而且还出现了红字的部分,这个应该怎么解决呢,急,急!!!请大神帮忙解决!
xtreg TE NUM OUTP INP GDP DEP MOR URB MIC,fe
Fixed-effects (within) regression Number of obs = 217
Group variable: province Number of groups = 31
R-sq: within = 0.2478 Obs per group: min = 7
between = 0.0024 avg = 7.0
overall = 0.0101 max = 7
F(8,178) = 7.33
corr(u_i, Xb) = -0.1811 Prob > F = 0.0000
------------------------------------------------------------------------------
TE | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
NUM | .0017666 .0006055 2.92 0.004 .0005716 .0029616
OUTP | -.0049714 .0016831 -2.95 0.004 -.0082928 -.00165
INP | .0012163 .0013924 0.87 0.384 -.0015315 .003964
GDP | 3.82e-07 3.84e-07 1.00 0.321 -3.75e-07 1.14e-06
DEP | -.0007537 .0011897 -0.63 0.527 -.0031014 .001594
MOR | .0053692 .0073359 0.73 0.465 -.0091073 .0198456
URB | -.0000119 .0015732 -0.01 0.994 -.0031164 .0030927
MIC | .0000542 .0001701 0.32 0.751 -.0002815 .0003898
_cons | .8690972 .0841274 10.33 0.000 .7030819 1.035113
-------------+----------------------------------------------------------------
sigma_u | .09799362
sigma_e | .02405531
rho | .94316525 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(30, 178) = 66.35 Prob > F = 0.0000
. estimates store FE
. xtreg TE NUM OUTP INP GDP DEP MOR URB MIC,re
Random-effects GLS regression Number of obs = 217
Group variable: province Number of groups = 31
R-sq: within = 0.2393 Obs per group: min = 7
between = 0.1155 avg = 7.0
overall = 0.1185 max = 7
Wald chi2(8) = 56.61
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
------------------------------------------------------------------------------
TE | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
NUM | .0018485 .0005661 3.27 0.001 .0007391 .002958
OUTP | -.00461 .0017029 -2.71 0.007 -.0079476 -.0012723
INP | .0013576 .0013886 0.98 0.328 -.001364 .0040792
GDP | 2.42e-07 3.68e-07 0.66 0.512 -4.81e-07 9.64e-07
DEP | .0007683 .0010968 0.70 0.484 -.0013815 .002918
MOR | .0041228 .0072149 0.57 0.568 -.0100181 .0182636
URB | -.0009316 .0010725 -0.87 0.385 -.0030338 .0011706
MIC | .0000728 .0001746 0.42 0.677 -.0002694 .0004149
_cons | .8701319 .0767427 11.34 0.000 .719719 1.020545
-------------+----------------------------------------------------------------
sigma_u | .07280207
sigma_e | .02405531
rho | .90156872 (fraction of variance due to u_i)
------------------------------------------------------------------------------
. estimates store RE
. hausman FE RE,constant sigmamore
Note: the rank of the differenced variance matrix (8) does not equal the number
of coefficients being tested (9); be sure this is what you expect, or
there may be problems computing the test. Examine the output of your
estimators for anything unexpected and possibly consider scaling your
variables so that the coefficients are on a similar scale.
---- Coefficients ----
| (b) (B) (b-B) sqrt(diag(V_b-V_B))
| FE RE Difference S.E.
-------------+----------------------------------------------------------------
NUM | .0017666 .0018485 -.0000819 .0002807
OUTP | -.0049714 -.00461 -.0003614 .000429
INP | .0012163 .0013576 -.0001413 .0004272
GDP | 3.82e-07 2.42e-07 1.41e-07 1.57e-07
DEP | -.0007537 .0007683 -.001522 .0005813
MOR | .0053692 .0041228 .0012464 .0025559
URB | -.0000119 -.0009316 .0009197 .0012426
MIC | .0000542 .0000728 -.0000186 .0000318
_cons | .8690972 .8701319 -.0010347 .0426087
------------------------------------------------------------------------------
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(8) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 14.96
Prob>chi2 = 0.0599
(V_b-V_B is not positive definite)