黃河泉 发表于 2017-10-26 08:16
请把你的 re/fe 之结果(还有指令)发出来,还有你的 hausman test 指令!
黄老师您好,我有一样的问题,麻烦您看下
. xtreg y x2 x3 x4 x5,fe
Fixed-effects (within) regression Number of obs = 224
Group variable: province Number of groups = 28
R-sq: Obs per group:
within = 0.7772 min = 8
between = 0.6730 avg = 8.0
overall = 0.6731 max = 8
F(4,192) = 167.44
corr(u_i, Xb) = -0.6325 Prob > F = 0.0000
------------------------------------------------------------------------------
y | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x2 | .0207524 .0102437 2.03 0.044 .0005479 .040957
x3 | .4202323 .0625765 6.72 0.000 .2968067 .543658
x4 | 1.207865 1.154845 1.05 0.297 -1.069947 3.485677
x5 | 1.489483 .2113146 7.05 0.000 1.072687 1.906279
_cons | -6117.054 843.726 -7.25 0.000 -7781.216 -4452.892
-------------+----------------------------------------------------------------
sigma_u | 6134.7585
sigma_e | 2374.9377
rho | .86966489 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(27, 192) = 22.66 Prob > F = 0.0000
. xtreg y x2 x3 x4 x5,re
Random-effects GLS regression Number of obs = 224
Group variable: province Number of groups = 28
R-sq: Obs per group:
within = 0.7693 min = 8
between = 0.6909 avg = 8.0
overall = 0.6970 max = 8
Wald chi2(4) = 654.82
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x2 | .0130925 .0091652 1.43 0.153 -.0048709 .0310559
x3 | .3515936 .059211 5.94 0.000 .2355421 .467645
x4 | .6421501 1.083607 0.59 0.553 -1.481681 2.765981
x5 | 1.838387 .2097731 8.76 0.000 1.427239 2.249535
_cons | -3889.929 1051.447 -3.70 0.000 -5950.727 -1829.132
-------------+----------------------------------------------------------------
sigma_u | 3804.75
sigma_e | 2374.9377
rho | .7196161 (fraction of variance due to u_i)
------------------------------------------------------------------------------
. estimates store fe
. estimates store re
. hausman fe re
Note: the rank of the differenced variance matrix (0) does not equal the number of coefficients
being tested (4); 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.
-------------+----------------------------------------------------------------
x2 | .0130925 .0130925 0 0
x3 | .3515936 .3515936 0 0
x4 | .6421501 .6421501 0 0
x5 | 1.838387 1.838387 0 0
------------------------------------------------------------------------------
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(0) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 0.00
Prob>chi2 = .
(V_b-V_B is not positive definite)
.
.
end of do-file
.