0% found this document useful (0 votes)
41 views8 pages

PC2 - Corregida

1. A VAR model with 2 lags was estimated using BC and DEMINT as endogenous variables and a constant as an exogenous variable. 2. The model is unstable as one root lies outside the unit circle. 3. Residual diagnostics show no autocorrelation according to the LM test.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
41 views8 pages

PC2 - Corregida

1. A VAR model with 2 lags was estimated using BC and DEMINT as endogenous variables and a constant as an exogenous variable. 2. The model is unstable as one root lies outside the unit circle. 3. Residual diagnostics show no autocorrelation according to the LM test.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

PASOS: EQUATION -> ARDL -> FIXED (2,2) -> @EXPAND(@QUARTER, @DROPLAST)

Dependent Variable: CONSUMO


Method: ARDL
Date: 12/05/22 Time: 16:48
Sample (adjusted): 1992 2020
Included observations: 29 after adjustments
Dependent lags: 2 (Fixed)
Dynamic regressors (2 lags, fixed): RENTA
Fixed regressors: @EXPAND(@QUARTER, @DROPLAST) C

Variable Coefficient Std. Error t-Statistic Prob.*

CONSUMO(-1) 1.049937 0.323746 3.243092 0.0036


CONSUMO(-2) -0.234265 0.318385 -0.735792 0.4693
RENTA 0.377525 0.063445 5.950435 0.0000
RENTA(-1) -0.219693 0.101353 -2.167601 0.0408
RENTA(-2) -0.040582 0.088485 -0.458637 0.6508
C 2463.544 4077.865 0.604126 0.5517

R-squared 0.994829 Mean dependent var 209865.8


Adjusted R-squared 0.993705 S.D. dependent var 79878.24
S.E. of regression 6337.644 Akaike info criterion 20.52839
Sum squared resid 9.24E+08 Schwarz criterion 20.81128
Log likelihood -291.6617 Hannan-Quinn criter. 20.61699
F-statistic 884.9888 Durbin-Watson stat 1.881564
Prob(F-statistic) 0.000000

*Note: p-values and any subsequent tests do not account for model
selection.
PASOS:
1. EQUATION -> ARDL -> FIXED (2,2) -> @EXPAND(@QUARTER, @DROPLAST)
2. VIEW -> COEFFICIENT DIAGNOSTICS -> LONG LONG RUN FORM AND BOUNDS TEST
ARDL Long Run Form and Bounds Test
Dependent Variable: D(CONSUMO)
Selected Model: ARDL(2, 2)
Case 2: Restricted Constant and No Trend
Date: 12/03/22 Time: 20:01
Sample: 1990 2020
Included observations: 29

Conditional Error Correction Regression

Variable Coefficient Std. Error t-Statistic Prob.

C 2463.544 4077.865 0.604126 0.5517


CONSUMO(-1)* -0.184328 0.082644 -2.230394 0.0358
RENTA(-1) 0.117250 0.050867 2.305050 0.0305
D(CONSUMO(-1)) 0.234265 0.318385 0.735792 0.4693
D(RENTA) 0.377525 0.063445 5.950435 0.0000
D(RENTA(-1)) 0.040582 0.088485 0.458637 0.6508

* p-value incompatible with t-Bounds distribution.

Levels Equation
Case 2: Restricted Constant and No Trend

Variable Coefficient Std. Error t-Statistic Prob.

RENTA 0.636098 0.072874 8.728788 0.0000


C 13365.03 19530.47 0.684317 0.5006

EC = CONSUMO - (0.6361*RENTA + 13365.0304)

F-Bounds Test Null Hypothesis: No levels relationship

Test Statistic Value Signif. I(0) I(1)

Asymptotic: n=1000
F-statistic 1.832172 10% 3.02 3.51
k 1 5% 3.62 4.16
2.5% 4.18 4.79
1% 4.94 5.58

Actual Sample Size 29 Finite Sample: n=35


10% 3.223 3.757
5% 3.957 4.53
1% 5.763 6.48

Finite Sample: n=30


10% 3.303 3.797
5% 4.09 4.663
1% 6.027 6.76
CON 1 REZAGO

1. VAR -> (1,1) -> LAG STRUCTURE -> AR ROOTS TABLE (IMAGEN 1)
2. LAG STRUCTURE -> LAGS EXCLUSION WALD TESTS (IMAGEN 2)
3. LAG STRUCTURE -> GRANGER CAUSALITY (BLOCK EXOGENEITY WALD TESTS
(IMAGEN 3)

Roots of Characteristic Polynomial VAR Granger Causality/Block Exogeneity Wald Tests


Endogenous variables: BC DEMINT Date: 12/03/22 Time: 20:16
Sample: 1994Q1 2004Q4
Exogenous variables: C
Included observations: 43
Lag specification: 1 1
Date: 12/03/22 Time: 20:11
Dependent variable: BC
Root Modulus
Excluded Chi-sq df Prob.
0.993136 0.993136
DEMINT 0.007436 1 0.9313
0.419232 0.419232
All 0.007436 1 0.9313
No root lies outside the unit circle.
VAR satisfies the stability condition.
Dependent variable: DEMINT
VAR Lag Exclusion Wald Tests
Date: 12/03/22 Time: 20:36 Excluded Chi-sq df Prob.
Sample (adjusted): 1994Q2 2004Q4
Included observations: 43 after adjustments BC 0.797273 1 0.3719

Chi-squared test statistics for lag exclusion: All 0.797273 1 0.3719


Numbers in [ ] are p-values

BC DEMINT Joint
Ambas probabilidades son mayores al 5%
Lag 1 198.5354 163.0795 221.9975 No hay causalidad.
[ 0.0000] [ 0.0000] [ 0.0000]

df 2 2 4
CON 2 REZAGOS
1. VAR -> (2,2) -> LAG STRUCTURE -> AR ROOTS TABLE (IMAGEN 1)

Roots of Characteristic Polynomial


Endogenous variables: BC DEMINT
Exogenous variables: C
Lag specification: 2 2
Date: 12/03/22 Time: 20:15

Root Modulus

-1.001962 1.001962
1.001962 1.001962
0.188971 0.188971
-0.188971 0.188971

Warning: At least one root outside the unit circle.


VAR does not satisfy the stability condition.

1. VAR -> (1,1) -> (IMAGEN 1)


2. VIEW -> RESIDUAL TESTS -> AUTOCORRELATION LM TEST
3. VIEW -> RESIDUAL TESTS -> CORRELOGRAMS (IMAGEN 2)
Vector Autoregression Estimates
Date: 12/03/22 Time: 20:42
Sample (adjusted): 1994Q2 2004Q4
Included observations: 43 after adjustments
Standard errors in ( ) & t-statistics in [ ]

BC DEMINT

BC(-1) 0.950367 -0.003522


(0.52648) (0.00394)
[ 1.80513] [-0.89290]

DEMINT(-1) -6.449419 0.462000


(74.7888) (0.56035)
[-0.08624] [ 0.82448]

C 677.5181 54.41055
(7582.09) (56.8085)
[ 0.08936] [ 0.95779]

R-squared 0.832310 0.803033


Adj. R-squared 0.823925 0.793184
Sum sq. resids 1095686. 61.50848
S.E. equation 165.5058 1.240045
F-statistic 99.26769 81.53976
Log likelihood -279.1467 -68.71082
Akaike AIC 13.12310 3.335387
Schwarz SC 13.24598 3.458261
Mean dependent -151.4860 102.4348
S.D. dependent 394.4254 2.726754

Determinant resid covariance (dof adj.) 2507.003


Determinant resid covariance 2169.391
Log likelihood -287.1961
Akaike information criterion 13.63703
Schwarz criterion 13.88277
Number of coefficients 6

1. OPEN -> EQUATION -> LS -> PROC -> MAKE RESIDUALS SERIES -> VIEW -> UNIT ROOT
TESTS -> STANDAR -> LEVEL (O PRIMERA DIFERENCIA), NONE
Null Hypothesis: D(RESID03) has a unit root
Exogenous: None
Lag Length: 2 (Automatic - based on SIC, maxlag=9)

t-Statistic Prob.*

Augmented Dickey-Fuller test statistic -7.094032 0.0000


Test critical values: 1% level -2.624057
5% level -1.949319
10% level -1.611711

*MacKinnon (1996) one-sided p-values.

Augmented Dickey-Fuller Test Equation


Dependent Variable: D(RESID03,2)
Method: Least Squares
Date: 12/03/22 Time: 21:15
Sample (adjusted): 1995Q1 2004Q4
Included observations: 40 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

D(RESID03(-1)) -2.305244 0.324955 -7.094032 0.0000


D(RESID03(-1),2) 0.869371 0.225345 3.857961 0.0004
D(RESID03(-2),2) 0.373812 0.145933 2.561526 0.0146

R-squared 0.711697 Mean dependent var 0.326910


Adjusted R-squared 0.696113 S.D. dependent var 79.44510
S.E. of regression 43.79484 Akaike info criterion 10.46895
Sum squared resid 70965.56 Schwarz criterion 10.59561
Log likelihood -206.3790 Hannan-Quinn criter. 10.51475
Durbin-Watson stat 1.892537

1. OPEN -> EQUATION -> COINTEGR -> VIEW -> COINTEGRATIO TEST -> ENGLE-GRANGER
Cointegration Test - Engle-Granger
Date: 12/03/22 Time: 21:21
Equation: UNTITLED
Specification: BC TCR C
Cointegrating equation deterministics: C
Null hypothesis: Series are not cointegrated
Automatic lag specification (lag=0 based on Schwarz info criterion,
maxlag=9)

Value Prob.*
Engle-Granger tau-statistic -0.778806 0.9357
Engle-Granger z-statistic -3.775117 0.8203

*MacKinnon (1996) p-values.

Intermediate Results:
Rho - 1 -0.087793
Rho S.E. 0.112728
Residual variance 27012.31
Long-run residual variance 27012.31
Number of lags 0
Number of observations 43
Number of stochastic trends** 2

**Number of stochastic trends in asymptotic distribution.

Engle-Granger Test Equation:


Dependent Variable: D(RESID)
Method: Least Squares
Date: 12/03/22 Time: 21:21
Sample (adjusted): 1994Q2 2004Q4
Included observations: 43 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

RESID(-1) -0.087793 0.112728 -0.778806 0.4405

R-squared 0.002175 Mean dependent var 17.98670


Adjusted R-squared 0.002175 S.D. dependent var 164.5332
S.E. of regression 164.3542 Akaike info criterion 13.06491
Sum squared resid 1134517. Schwarz criterion 13.10586
Log likelihood -279.8955 Hannan-Quinn criter. 13.08001
Durbin-Watson stat 2.109703

EQUATION -> ARDL -> AUTOMATIC


Dependent Variable: CONSUMO
Method: ARDL
Date: 12/03/22 Time: 21:23
Sample (adjusted): 1994 2020
Included observations: 27 after adjustments
Maximum dependent lags: 4 (Automatic selection)
Model selection method: Akaike info criterion (AIC)
Dynamic regressors (4 lags, automatic): RENTA
Fixed regressors: @EXPAND(@QUARTER, @DROPLAST) C
Number of models evalulated: 20
Selected Model: ARDL(3, 4)

Variable Coefficient Std. Error t-Statistic Prob.*

CONSUMO(-1) 0.118050 0.158770 0.743530 0.4668


CONSUMO(-2) -0.025707 0.221621 -0.115993 0.9089
CONSUMO(-3) 0.220913 0.151915 1.454189 0.1631
RENTA 0.628054 0.033841 18.55920 0.0000
RENTA(-1) 0.012456 0.043916 0.283639 0.7799
RENTA(-2) -0.037255 0.042612 -0.874292 0.3935
RENTA(-3) -0.053640 0.042157 -1.272387 0.2194
RENTA(-4) -0.074373 0.030612 -2.429553 0.0258
C -6619.478 1962.112 -3.373650 0.0034

R-squared 0.999350 Mean dependent var 217169.5


Adjusted R-squared 0.999061 S.D. dependent var 77895.18
S.E. of regression 2387.360 Akaike info criterion 18.65497
Sum squared resid 1.03E+08 Schwarz criterion 19.08691
Log likelihood -242.8420 Hannan-Quinn criter. 18.78341
F-statistic 3457.692 Durbin-Watson stat 1.294430
Prob(F-statistic) 0.000000

*Note: p-values and any subsequent tests do not account for model
selection.

You might also like