悬赏 5 个论坛币 未解决
我做的是二分变量的一组面板数据,准备用Logit模型回归,进行Hausman固定效应和随机效应检验时,由于变量的共线性都被剔除了,无法得到检验结果。不知道是数据出了什么问题。求指点!
. qui xtreg y x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 x11 x12 x13 x14 x15,fe
. est store fe
. qui xtreg y x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 x11 x12 x13 x14 x15,re
. est store re
. hausman fe
nothing to test
r(498);
. xtreg y x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 x11 x12 x13 x14 x15,fe
note: x1 omitted because of collinearity
note: x2 omitted because of collinearity
note: x3 omitted because of collinearity
note: x4 omitted because of collinearity
note: x5 omitted because of collinearity
note: x6 omitted because of collinearity
note: x7 omitted because of collinearity
note: x8 omitted because of collinearity
note: x9 omitted because of collinearity
note: x10 omitted because of collinearity
note: x11 omitted because of collinearity
note: x12 omitted because of collinearity
note: x13 omitted because of collinearity
note: x14 omitted because of collinearity
note: x15 omitted because of collinearity
Fixed-effects (within) regression Number of obs = 1621
Group variable: rank Number of groups = 334
R-sq: within = . Obs per group: min = 3
between = . avg = 4.9
overall = . max = 5
F(15,1272) = .
corr(u_i, Xb) = . Prob > F = .
------------------------------------------------------------------------------
y | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x1 | (omitted)
x2 | (omitted)
x3 | (omitted)
x4 | (omitted)
x5 | (omitted)
x6 | (omitted)
x7 | (omitted)
x8 | (omitted)
x9 | (omitted)
x10 | (omitted)
x11 | (omitted)
x12 | (omitted)
x13 | (omitted)
x14 | (omitted)
x15 | (omitted)
_cons | .5009254 . . . . .
-------------+----------------------------------------------------------------
sigma_u | .50075019
sigma_e | 0
rho | 1 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(333, 1272) = . Prob > F = .
. xtreg y x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 x11 x12 x13 x14 x15,re
Random-effects GLS regression Number of obs = 1621
Group variable: rank Number of groups = 334
R-sq: within = 0.0000 Obs per group: min = 3
between = 0.0000 avg = 4.9
overall = 0.0000 max = 5
Wald chi2(0) = .
corr(u_i, X) = 0 (assumed) Prob > chi2 = .
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x1 | (omitted)
x2 | (omitted)
x3 | (omitted)
x4 | (omitted)
x5 | (omitted)
x6 | (omitted)
x7 | (omitted)
x8 | (omitted)
x9 | (omitted)
x10 | (omitted)
x11 | (omitted)
x12 | (omitted)
x13 | (omitted)
x14 | (omitted)
x15 | (omitted)
_cons | (omitted)
-------------+----------------------------------------------------------------
sigma_u | .50796673
sigma_e | 0
rho | 1 (fraction of variance due to u_i)
------------------------------------------------------------------------------
. hausman fe
nothing to test