ANNEXE
ANNEXE1 : Les différents tests pour le modèle
à
effets aléatoires : cas de l'igname
|
.xtreg lprod lsup lprix lpoprur lhautpl,
Fixed-effects (within) regression Group variable:
comm
|
fe
|
Number of obs =
Number of groups =
|
110
10
|
|
R-sq:
|
within
|
= 0.5881
|
|
|
Obs per group: min =
|
11
|
|
between
|
= 0.0213
|
|
|
avg =
|
11.0
|
|
overall
|
= 0.1598
|
|
|
max =
|
11
|
|
|
|
|
|
F(4,96) =
|
34.27
|
|
corr(u_i, Xb)
|
= -0.5174
|
|
|
Prob > F =
|
0.0000
|
|
lprod |
|
Coef.
|
Std. Err.
|
t
|
P>|t| [95% Conf.
|
Interval]
|
|
+
|
|
|
|
|
|
|
lsup |
|
1.079401
|
.099143
|
10.89
|
0.000 .8826035
|
1.276198
|
|
lprix |
|
-.0148019
|
.1126685
|
-0.13
|
0.896 -.2384471
|
.2088433
|
|
lpoprur |
|
.8802428
|
.3193749
|
2.76
|
0.007 .2462886
|
1.514197
|
|
lhautpl |
|
-.2606049
|
.2758427
|
-0.94
|
0.347 -.8081484
|
.2869386
|
|
|
_cons
|
-6.245125
|
3.696577
|
-1.69
|
0.094 -13.58277
|
1.092522
|
|
+
|
|
|
|
|
|
|
sigma_u |
|
.87757312
|
|
|
|
|
|
sigma_e |
|
.41960687
|
|
|
|
|
|
rho |
|
.8139198
|
(fraction of variance due to u_i)
|
|
|
F test that all u_i=0: F(9, 96) =
|
26.54
|
Prob > F =
|
0.0000
|
|
. est store fixed
. xtreg lprod lsup lprix lpoprur lhautpl, Random-effects
GLS regression
|
re
|
Number of obs =
|
110
|
|
Group variable: comm
|
|
Number of groups =
|
10
|
|
R-sq: within = 0.5800
|
|
Obs per group: min =
|
11
|
|
between = 0.0362
|
|
avg =
|
11.0
|
|
overall = 0.2260
|
|
max =
|
11
|
|
Random effects u_i ~ Gaussian
|
|
Wald chi2(4) =
|
126.01
|
|
corr(u_i, X) = 0 (assumed)
|
|
Prob > chi2 =
|
0.0000
|
|
lprod
|
|
|
Coef.
|
Std. Err.
|
z
|
P>|z|
|
[95% Conf.
|
Interval]
|
|
+
|
|
|
|
|
|
|
|
|
lsup
|
|
|
1.08131
|
.1014423
|
10.66
|
0.000
|
.882487
|
1.280133
|
|
lprix
|
|
|
.0274313
|
.1142362
|
0.24
|
0.810
|
-.1964676
|
.2513301
|
|
lpoprur
|
|
|
.4357262
|
.2589625
|
1.68
|
0.092
|
-.0718309
|
.9432834
|
|
lhautpl
|
|
|
-.1912055
|
.2820628
|
-0.68
|
0.498
|
-.7440384
|
.3616274
|
|
_cons
|
|
|
-2.066495
|
3.256456
|
-0.63
|
0.526
|
-8.449032
|
4.316042
|
|
+
|
|
|
|
|
|
|
|
|
sigma_u
|
|
|
.60676555
|
|
|
|
|
|
|
sigma_e
|
|
|
.41960687
|
|
|
|
|
|
|
rho
|
|
|
.67648142
|
(fraction of variance due
|
to u_i)
|
|
. hausman fixed
|
|
|
Réalisé et soutenu par Samson James Aimé
AGBO et Rodrigue Noutaï HONKPEHEDJI
|
|
|
|
---- Coefficients ----
|
|
|
|
|
|
(b)
|
(B)
|
(b-B)
|
sqrt(diag(V_b-V_B))
|
|
|
|
fixed
|
.
|
Difference
|
S.E.
|
|
+
|
|
|
|
|
|
lsup |
|
1.079401
|
1.08131
|
-.0019093
|
.
|
|
lprix |
|
-.0148019
|
.0274313
|
-.0422332
|
.
|
|
lpoprur |
|
.8802428
|
.4357262
|
.4445165
|
.1869191
|
|
lhautpl |
|
-.2606049
|
-.1912055
|
-.0693994
|
.
|
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(4) =
(b-B)'[(V_b-V_B)^(-1)](b-B)
= 5.46
Prob>chi2 = 0.2432
(V_b-V_B is not positive definite)
. xttest0
Breusch and Pagan Lagrangian multiplier test for random
effects lprod[comm,t] = Xb + u[comm] + e[comm,t]
Estimated results:
| Var sd = sqrt(Var)
+
lprod | .7942038 .8911811
e | .1760699 .4196069
u | .3681644 .6067655
Test: Var(u) = 0
chi2(1) = 217.47
Prob > chi2 = 0.0000
. sktest fixed
variable fixed not found r(111);
. predict fixed, u . sktest fixed
Skewness/Kurtosis tests for Normality
joint
Variable | Pr(Skewness) Pr(Kurtosis) adj chi2(2)
Prob>chi2
+
fixed | 0.000 0.009 21.14 0.0000
. xtregar lprod lsup lprix lpoprur lhautpl, re
lbi
RE GLS regression with AR(1) disturbances Number of obs =
110
Group variable: comm Number of groups = 10
R-sq: within = 0.5771 Obs per group: min = 11
between = 0.0402 avg = 11.0
overall = 0.2382 max = 11
Wald chi2(5) = 121.13
corr(u_i, Xb) = 0 (assumed) Prob > chi2 =
0.0000
lprod | Coef. Std. Err. z P>|z| [95% Conf.
Interval]
+
|
|
|
d
|
Réalisé et soutenu par Samson James Aimé
AGBO et Rodrigue Noutaï HONKPEHEDJI
|
|
|
|
lsup
|
|
|
1.084781
|
.1033118 10.50 0.000
|
.8822936
|
1.287268
|
|
lprix
|
|
|
.0336269
|
.1157967 0.29 0.772
|
-.1933305
|
.2605843
|
|
lpoprur
|
|
|
.3652185
|
.2548147 1.43 0.152
|
-.1342091
|
.8646461
|
|
lhautpl
|
|
|
-.1887518
|
.2858858 -0.66 0.509
|
-.7490777
|
.3715741
|
|
_cons
|
|
|
-1.373301
|
3.246207 -0.42 0.672
|
-7.73575
|
4.989149
|
|
+
|
|
|
|
|
|
|
rho_ar
|
|
|
-.01993378
|
(estimated autocorrelation
|
coefficient)
|
|
|
sigma_u
|
|
|
.55980321
|
|
|
|
|
sigma_e
|
|
|
.44552279
|
|
|
|
|
rho_fov
|
|
|
.61222481
|
(fraction of variance due
|
to u_i)
|
|
|
theta
|
|
|
.77059653
|
|
|
|
modified Bhargava et al. Durbin-Watson = 2.0383967
Baltagi-Wu LBI = 2.1303588
| 
