Ejercicio 17
17. Considere las series de tiempo de dividendos y utilidades dadas en la hoja 8 del archivo
1 2 t t Dividendos Utilidades u
a) ¿La regresión presenta regresión espuria? ¿Por qué?
Al realizar la regresión obtuvimos los resultados y vimos que la R2 es mayor al DurbinWhattson. Esto es claramente una regresión espuria
Dependent Variable: DIVIDENDOS
Method: Least Squares
Date: 10/29/15 Time: 12:08
Sample: 1970Q1 1991Q4
Included observations: 88
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
-13.31143
7.362611
-1.807977
0.0741
UTILIDADES
0.628156
0.052674
11.92531
0.0000
R-squared
0.623159
Mean dependent var69.16477
Adjusted R-squared
0.618777
S.D. dependent var
38.36447
S.E. of regression
23.68747
Akaike info criterion
9.190234
Sum squared resid
48254.27
Schwarz criterion
9.246538
Log likelihood
-402.3703
Hannan-Quinn criter.
9.212918
F-statistic
142.2130
Durbin-Watson stat
0.071211
Prob(F-statistic)
0.000000
b) ¿están Cointegradas las series de tiempo dedividendos y utilidades? ¿Cómo probar esto explícitamente? Si después de la prueba se encuentra que están cointegradas, cambiara la respuesta en a.
Null Hypothesis: D(DIVIDENDOS) has a unit root
Exogenous: Constant
Lag Length: 1 (Automatic - based on SIC, maxlag=11)
t-Statistic
Prob.*
Augmented Dickey-Fuller test statistic
-6.060137
0.0000
Test critical values:
1% level-3.509281
5% level
-2.895924
10% level
-2.585172
*MacKinnon (1996) one-sided p-values.
Augmented Dickey-Fuller Test Equation
Dependent Variable: D(DIVIDENDOS,2)
Method: Least Squares
Date: 10/29/15 Time: 12:14
Sample (adjusted): 1970Q4 1991Q4
Included observations: 85 after adjustments
Variable
Coefficient
Std. Error
t-Statistic
Prob. D(DIVIDENDOS(-1))
-0.442549
0.073026
-6.060137
0.0000
D(DIVIDENDOS(-1),2)
0.495745
0.095345
5.199515
0.0000
C
0.594678
0.155552
3.823028
0.0003
R-squared
0.362985
Mean dependent var
0.011765
Adjusted R-squared
0.347448
S.D. dependent var
1.385160
S.E. of regression
1.118942
Akaike info criterion
3.097301
Sum squared resid
102.6666
Schwarz criterion
3.183512
Log likelihood-128.6353
Hannan-Quinn criter.
3.131978
F-statistic
23.36267
Durbin-Watson stat
2.075511
Prob(F-statistic)
0.000000
La variable es estacionaria en primeras direfencias, l Vriable dividendo esta intebgrada enorden (1)
Null Hypothesis: D(UTILIDADES) has a unit root
Exogenous: Constant
Lag Length: 0 (Automatic - based on SIC, maxlag=11)
t-Statistic
Prob.*Augmented Dickey-Fuller test statistic
-6.964739
0.0000
Test critical values:
1% level
-3.508326
5% level
-2.895512
10% level
-2.584952
*MacKinnon (1996) one-sided p-values.
Augmented Dickey-Fuller Test Equation
Dependent Variable: D(UTILIDADES,2)
Method: Least Squares
Date: 10/29/15 Time: 12:15
Sample (adjusted): 1970Q3 1991Q4
Included observations: 86 afteradjustments
Variable
Coefficient
Std. Error
t-Statistic
Prob.
D(UTILIDADES(-1))
-0.731947
0.105093
-6.964739
0.0000
C
1.244874
0.992431
1.254368
0.2132
R-squared
0.366074
Mean dependent var
0.011628
Adjusted R-squared
0.358527
S.D. dependent var
11.30669
S.E. of regression
9.055755
Akaike info criterion
7.267659
Sum squared resid
6888.562
Schwarzcriterion
7.324737
Log likelihood
-310.5093
Hannan-Quinn criter.
7.290630
F-statistic
48.50758
Durbin-Watson stat
1.995310
Prob(F-statistic)
0.000000
la variable utilidaes esta integrada en orden 1
Ambas variables están integradas en el mismo orden orden (1).
Null Hypothesis: RESID01 has a unit root
Exogenous: Constant
Lag Length: 0 (Automatic - based on SIC, maxlag=11)...
Regístrate para leer el documento completo.