xtreg le fdi lpgdp ltr lppi leduc lfir lrd fdit fdie t,fe
Fixed-effects (within) regression Number of obs = 464
Group variable: reg Number of groups = 29
R-sq: within = 0.9799 Obs per group: min = 16
between = 0.7262 avg = 16.0
overall = 0.8736 max = 16
F(10,425) = 2072.88
corr(u_i, Xb) = -0.2636 Prob > F = 0.0000
------------------------------------------------------------------------------
le | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
fdi | .007928 .0066403 1.19 0.233 -.0051239 .0209799
lpgdp | -1.01409 .0076315 -132.88 0.000 -1.02909 -.9990894
ltr | -.0937027 .0300447 -3.12 0.002 -.1527575 -.0346479
lppi | .0588617 .0213048 2.76 0.006 .0169857 .1007376
leduc | .288121 .038212 7.54 0.000 .213013 .363229
lfir | -.3961882 .0516029 -7.68 0.000 -.4976169 -.2947595
lrd | .0812423 .014707 5.52 0.000 .0523347 .1101499
fdit | -.0119771 .0085668 -1.40 0.163 -.0288157 .0048614
fdie | .0099902 .0060993 1.64 0.102 -.0019984 .0219789
t | .0489636 .007362 6.65 0.000 .034493 .0634342
_cons | 18.32826 .2608042 70.28 0.000 17.81563 18.84088
-------------+----------------------------------------------------------------
sigma_u | .47003347
sigma_e | .15500968
rho | .9019103 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(28, 425) = 99.24 Prob > F = 0.0000
.
. estimate store fe1
.
. xtivreg le lpgdp ltr lppi leduc lfir lrd fdit fdie t (fdi=l(1/2).fdi),fe
Fixed-effects (within) IV regression Number of obs = 406
Group variable: reg Number of groups = 29
R-sq: within = 0.9832 Obs per group: min = 14
between = 0.7164 avg = 14.0
overall = 0.8696 max = 14
Wald chi2(10) = 3.02e+06
corr(u_i, Xb) = -0.2393 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
le | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
fdi | .0238142 .0120082 1.98 0.047 .0002785 .0473499
lpgdp | -1.008111 .007618 -132.33 0.000 -1.023042 -.9931796
ltr | -.1270153 .0321445 -3.95 0.000 -.1900174 -.0640131
lppi | .0412078 .020928 1.97 0.049 .0001896 .082226
leduc | .2756213 .0382407 7.21 0.000 .2006709 .3505716
lfir | -.34509 .0570147 -6.05 0.000 -.4568368 -.2333431
lrd | .0762162 .0142471 5.35 0.000 .0482925 .10414
fdit | -.0202332 .0101108 -2.00 0.045 -.04005 -.0004164
fdie | .0115757 .0062832 1.84 0.065 -.0007392 .0238906
t | .0572396 .0073348 7.80 0.000 .0428637 .0716154
_cons | 18.1484 .2631795 68.96 0.000 17.63258 18.66423
-------------+----------------------------------------------------------------
sigma_u | .48264944
sigma_e | .14178631
rho | .920557 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(28,367) = 110.15 Prob > F = 0.0000
------------------------------------------------------------------------------
Instrumented: fdi
Instruments: lpgdp ltr lppi leduc lfir lrd fdit fdie t L.fdi L2.fdi
------------------------------------------------------------------------------
.
. estimate store fe_iv
.
. hausman fe1 fe_iv
---- Coefficients ----
| (b) (B) (b-B) sqrt(diag(V_b-V_B))
| fe1 fe_iv Difference S.E.
-------------+----------------------------------------------------------------
fdi | .007928 .0238142 -.0158862 .
lpgdp | -1.01409 -1.008111 -.005979 .0004533
ltr | -.0937027 -.1270153 .0333126 .
lppi | .0588617 .0412078 .0176538 .0039891
leduc | .288121 .2756213 .0124997 .
lfir | -.3961882 -.34509 -.0510982 .
lrd | .0812423 .0762162 .0050261 .0036494
fdit | -.0119771 -.0202332 .0082561 .
fdie | .0099902 .0115757 -.0015855 .
t | .0489636 .0572396 -.0082759 .0006331
------------------------------------------------------------------------------
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtivreg
Test: Ho: difference in coefficients not systematic
chi2(10) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= -6.26 chi2<0 ==> model fitted on these
data fails to meet the asymptotic
assumptions of the Hausman test;
see suest for a generalized test
.
. hausman fe1 fe_iv,sigmaless
---- Coefficients ----
| (b) (B) (b-B) sqrt(diag(V_b-V_B))
| fe1 fe_iv Difference S.E.
-------------+----------------------------------------------------------------
fdi | .007928 .0238142 -.0158862 .0055138
lpgdp | -1.01409 -1.008111 -.005979 .0072615
ltr | -.0937027 -.1270153 .0333126 .028365
lppi | .0588617 .0412078 .0176538 .0203054
leduc | .288121 .2756213 .0124997 .0363497
lfir | -.3961882 -.34509 -.0510982 .0485201
lrd | .0812423 .0762162 .0050261 .0140365
fdit | -.0119771 -.0202332 .0082561 .0079802
fdie | .0099902 .0115757 -.0015855 .0057839
t | .0489636 .0572396 -.0082759 .0070065
------------------------------------------------------------------------------
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtivreg
Test: Ho: difference in coefficients not systematic
chi2(10) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 25.06
Prob>chi2 = 0.0052
.
. hausman fe1 fe_iv,sigmamore
---- Coefficients ----
| (b) (B) (b-B) sqrt(diag(V_b-V_B))
| fe1 fe_iv Difference S.E.
-------------+----------------------------------------------------------------
fdi | .007928 .0238142 -.0158862 .0178935
lpgdp | -1.01409 -1.008111 -.005979 .0235653
ltr | -.0937027 -.1270153 .0333126 .0920515
lppi | .0588617 .0412078 .0176538 .065896
leduc | .288121 .2756213 .0124997 .1179638
lfir | -.3961882 -.34509 -.0510982 .1574597
lrd | .0812423 .0762162 .0050261 .045552
fdit | -.0119771 -.0202332 .0082561 .0258976
fdie | .0099902 .0115757 -.0015855 .0187701
t | .0489636 .0572396 -.0082759 .0227379
------------------------------------------------------------------------------
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtivreg
Test: Ho: difference in coefficients not systematic
chi2(10) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 2.38
Prob>chi2 = 0.9925
.
. dmexogxt
Davidson-MacKinnon test of exogeneity: .2246426 F( 1,366) P-value = .6358
.
|