| hausman 检验统计量为负,可以认为是原假设不成立,应该采用 FE。前面的开头出现的note有没有什么问题?接下来该如何处理?谢谢! |
Fixed-effects (within) regression Number of obs = 77
Group variable: nation Number of groups = 11
R-sq: within = 0.1722 Obs per group: min = 7
between = 0.1846 avg = 7.0
overall = 0.1579 max = 7
F(5,61) = 2.54
corr(u_i, Xb) = 0.2097 Prob > F = 0.0376
------------------------------------------------------------------------------
iia | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
gdpr | 6.586579 6.061125 1.09 0.281 -5.533389 18.70655
agdp | -.0002467 .0001562 -1.58 0.120 -.0005591 .0000657
agdp2 | 2.47e-09 1.95e-09 1.27 0.210 -1.43e-09 6.38e-09
ise23 | 55.08584 52.6844 1.05 0.300 -50.26314 160.4348
vie | 22.36356 9.26039 2.41 0.019 3.846268 40.88086
_cons | -10.74977 44.12782 -0.24 0.808 -98.98879 77.48925
-------------+----------------------------------------------------------------
sigma_u | 7.9447032
sigma_e | 2.8981233
rho | .88255843 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(10, 61) = 40.98 Prob > F = 0.0000
. est store fe
. xtreg iia gdpr agdp agdp2 ise23 vie,re
Random-effects GLS regression Number of obs = 77
Group variable: nation Number of groups = 11
R-sq: within = 0.1674 Obs per group: min = 7
between = 0.2228 avg = 7.0
overall = 0.2011 max = 7
Wald chi2(5) = 14.26
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0140
------------------------------------------------------------------------------
iia | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
gdpr | 7.628021 6.138853 1.24 0.214 -4.40391 19.65995
agdp | -.0002531 .0001493 -1.69 0.090 -.0005457 .0000396
agdp2 | 2.51e-09 1.91e-09 1.31 0.189 -1.24e-09 6.27e-09
ise23 | 80.0909 40.79829 1.96 0.050 .1277159 160.0541
vie | 23.25341 8.856134 2.63 0.009 5.895704 40.61111
_cons | -32.7159 34.24825 -0.96 0.339 -99.84124 34.40945
-------------+----------------------------------------------------------------
sigma_u | 5.8957149
sigma_e | 2.8981233
rho | .80538933 (fraction of variance due to u_i)
------------------------------------------------------------------------------
. est store re
. hausman fe re
Note: the rank of the differenced variance matrix (3) does not equal the number of
coefficients being tested (5); 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.
-------------+----------------------------------------------------------------
gdpr | 6.586579 7.628021 -1.041441 .
agdp | -.0002467 -.0002531 6.37e-06 .000046
agdp2 | 2.47e-09 2.51e-09 -4.09e-11 3.80e-10
ise23 | 55.08584 80.0909 -25.00506 33.33385
vie | 22.36356 23.25341 -.8898461 2.706235
------------------------------------------------------------------------------
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(3) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= -4.39 chi2<0 ==> model fitted on these
data fails to meet the asymptotic
assumptions of the Hausman test;
see suest for a generalized test


雷达卡







京公网安备 11010802022788号







