我的运行结果:
xtreg whetherornot ex1 cr z1 h5 size leverage boardsize directorrate cashcapital ssp ts y1-y4 a1-a9,fe
Fixed-effects (within) regression Number of obs = 344
Group variable (i): no Number of groups = 86
R-sq: within = 0.1029 Obs per group: min = 4
between = 0.0005 avg = 4.0
overall = 0.0052 max = 4
F(14,244) = 2.00
corr(u_i, Xb) = -0.4269 Prob > F = 0.0185
------------------------------------------------------------------------------
whetherornot | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ex1 | -.0035516 .0031429 -1.13 0.260 -.0097424 .0026391
cr | .0244831 .0086974 2.82 0.005 .0073516 .0416146
z1 | -.0003347 .003167 -0.11 0.916 -.0065729 .0059035
-------------+----------------------------------------------------------------
sigma_u | .48666473
sigma_e | .2811591
rho | .74975565 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(85, 244) = 6.34 Prob > F = 0.0000
. xtreg whetherornot ex1 cr z1 h5 size leverage boardsize directorrate cashcapital ssp ts y1-y4 a1-a9,re
Random-effects GLS regression Number of obs = 344
Group variable (i): no Number of groups = 86
R-sq: within = 0.0477 Obs per group: min = 4
between = 0.2756 avg = 4.0
overall = 0.2183 max = 4
Random effects u_i ~ Gaussian Wald chi2(23) = 41.29
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0110
------------------------------------------------------------------------------
whetherornot | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ex1 | -.0049465 .0028042 -1.76 0.078 -.0104426 .0005495
cr | .0081929 .0060879 1.35 0.178 -.0037392 .020125
z1 | -.0003532 .0025203 -0.14 0.889 -.005293 .0045866
-------------+----------------------------------------------------------------
sigma_u | .35045702
sigma_e | .2811591
rho | .60841027 (fraction of variance due to u_i)
------------------------------------------------------------------------------
. xttest0
Breusch and Pagan Lagrangian multiplier test for random effects:
whetherornot[no,t] = Xb + u[no] + e[no,t]
Estimated results:
| Var sd = sqrt(Var)
---------+-----------------------------
whether~t | .2495084 .4995082
e | .0790504 .2811591
u | .1228201 .350457
Test: Var(u) = 0
chi2(1) = 132.56
Prob > chi2 = 0.0000
. qui xtreg whetherornot ex1 cr z1 h5 size leverage boardsize directorrate cashcapital ssp ts y1-y4 a1-a9,fe
. est store fe
. qui xtreg whetherornot ex1 cr z1 h5 size leverage boardsize directorrate cashcapital ssp ts y1-y4 a1-a9,re
. est store re
. hausman fe
---- Coefficients ----
| (b) (B) (b-B) sqrt(diag(V_b-V_B))
| fe re Difference S.E.
-------------+----------------------------------------------------------------
ex1 | -.0035516 -.0049465 .0013949 .0014194
cr | .0244831 .0081929 .0162903 .0062114
z1 | -.0003347 -.0003532 .0000185 .0019178
------------------------------------------------------------------------------
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(14) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 34.98
Prob>chi2 = 0.0015
看了坛子里的一些资料,似乎应该选择固定效应模型,可是固定效应模型的R2较小,而且也不大符合经济含义,请问,该怎么选择?谢谢!!!