ANNEXES
A. LA STATIONNARITE DES SERIES
1. Série taux d'inflation
Null Hypothesis: TXINFL has a unit root
|
|
Exogenous: Constant
|
|
|
Lag Length: 0 (Automatic - based on SIC, maxlag=4)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t-Statistic
|
Prob.*
|
|
|
|
|
|
|
|
|
|
|
Augmented Dickey-Fuller test statistic
|
-22.62535
|
0.0000
|
Test critical values:
|
1% level
|
|
-3.808546
|
|
|
5% level
|
|
-3.020686
|
|
|
10% level
|
|
-2.650413
|
|
|
|
|
|
|
|
|
|
|
|
*MacKinnon (1996) one-sided p-values.
|
|
|
|
|
|
|
|
|
|
|
|
Augmented Dickey-Fuller Test Equation
|
|
Dependent Variable: D(TXINFL)
|
|
|
Method: Least Squares
|
|
|
Date: 11/08/22 Time: 09:35
|
|
|
Sample (adjusted): 2001 2020
|
|
|
Included observations: 20 after adjustments
|
|
|
|
|
|
|
|
|
|
|
|
Variable
|
Coefficient
|
Std. Error
|
t-Statistic
|
Prob.
|
|
|
|
|
|
|
|
|
|
|
TXINFL(-1)
|
-0.770489
|
0.034054
|
-22.62535
|
0.0000
|
C
|
10.46553
|
4.086284
|
2.561136
|
0.0196
|
|
|
|
|
|
|
|
|
|
|
R-squared
|
0.966032
|
Mean dependent var
|
-24.77200
|
Adjusted R-squared
|
0.964145
|
S.D. dependent var
|
89.22401
|
S.E. of regression
|
16.89503
|
Akaike info criterion
|
8.586556
|
Sum squared resid
|
5137.958
|
Schwarz criterion
|
8.686129
|
Log likelihood
|
-83.86556
|
Hannan-Quinn criter.
|
8.605994
|
F-statistic
|
511.9063
|
Durbin-Watson stat
|
2.077977
|
Prob(F-statistic)
|
0.000000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
La Stationnarité de la série taux
d'inflation (TXINF) est en niveau
2. Série taux de change
Les tests informels de stationnarité renseignent que la
série taux de change (TXCH) n'est pas stationnaire en moyenne en niveau.
Ce résultat est par ailleurs confirmé par le test formel de
Dickey Fuller augmenté : la série sous étude n'est
pas stationnaire quel que soit le seuil statistique. Le processus est de type
DS.
Null Hypothesis: TXCH has a unit root
|
|
Exogenous: None
|
|
|
Lag Length: 0 (Automatic - based on SIC, maxlag=4)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t-Statistic
|
Prob.*
|
|
|
|
|
|
|
|
|
|
|
Augmented Dickey-Fuller test statistic
|
3.460764
|
0.9994
|
Test critical values:
|
1% level
|
|
-2.685718
|
|
|
5% level
|
|
-1.959071
|
|
|
10% level
|
|
-1.607456
|
|
|
|
|
|
|
|
|
|
|
|
*MacKinnon (1996) one-sided p-values.
|
|
|
|
|
|
|
|
|
|
|
|
Augmented Dickey-Fuller Test Equation
|
|
Dependent Variable: D(TXCH)
|
|
|
Method: Least Squares
|
|
|
Date: 11/08/22 Time: 09:38
|
|
|
Sample (adjusted): 2001 2020
|
|
|
Included observations: 20 after adjustments
|
|
|
|
|
|
|
|
|
|
|
|
Variable
|
Coefficient
|
Std. Error
|
t-Statistic
|
Prob.
|
|
|
|
|
|
|
|
|
|
|
TXCH(-1)
|
0.102615
|
0.029651
|
3.460764
|
0.0026
|
|
|
|
|
|
|
|
|
|
|
R-squared
|
-0.052874
|
Mean dependent var
|
97.49850
|
Adjusted R-squared
|
-0.052874
|
S.D. dependent var
|
118.1702
|
S.E. of regression
|
121.2540
|
Akaike info criterion
|
12.48236
|
Sum squared resid
|
279348.2
|
Schwarz criterion
|
12.53215
|
Log likelihood
|
-123.8236
|
Hannan-Quinn criter.
|
12.49208
|
Durbin-Watson stat
|
1.444516
|
|
|
|
|
|
|
|
|
|
|
|
|
|
La Stationnarité de la série taux de
change (TXCH) est prise en différence première :
Nous procédons à la stationnarisation par
différence première. L'application des tests ADF sur la
série en différence première confirme la
stationnarité de la série. La valeur de la probabilité
critique d'acceptation est inférieure au seuil d'acceptation (ou de
signification) de 1%. La série taux de change (TXCH), en
différence première est donc un processus stationnaire.
Null Hypothesis: D(TXCH) has a unit root
|
|
Exogenous: None
|
|
|
Lag Length: 0 (Automatic - based on SIC, maxlag=4)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t-Statistic
|
Prob.*
|
|
|
|
|
|
|
|
|
|
|
Augmented Dickey-Fuller test statistic
|
-1.997004
|
0.0463
|
Test critical values:
|
1% level
|
|
-2.692358
|
|
|
5% level
|
|
-1.960171
|
|
|
10% level
|
|
-1.607051
|
|
|
|
|
|
|
|
|
|
|
|
*MacKinnon (1996) one-sided p-values.
|
|
Warning: Probabilities and critical values calculated for 20
observations
|
and may not be
accurate for a sample size of 19
|
|
|
|
|
|
|
|
|
|
|
Augmented Dickey-Fuller Test Equation
|
|
Dependent Variable: D(TXCH,2)
|
|
|
Method: Least Squares
|
|
|
Date: 11/08/22 Time: 09:40
|
|
|
Sample (adjusted): 2002 2020
|
|
|
Included observations: 19 after adjustments
|
|
|
|
|
|
|
|
|
|
|
|
Variable
|
Coefficient
|
Std. Error
|
t-Statistic
|
Prob.
|
|
|
|
|
|
|
|
|
|
|
D(TXCH(-1))
|
-0.426736
|
0.213688
|
-1.997004
|
0.0612
|
|
|
|
|
|
|
|
|
|
|
R-squared
|
0.179848
|
Mean dependent var
|
5.997368
|
Adjusted R-squared
|
0.179848
|
S.D. dependent var
|
142.7740
|
S.E. of regression
|
129.2993
|
Akaike info criterion
|
12.61333
|
Sum squared resid
|
300929.7
|
Schwarz criterion
|
12.66304
|
Log likelihood
|
-118.8267
|
Hannan-Quinn criter.
|
12.62175
|
Durbin-Watson stat
|
1.649149
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|