Vectores Autorregresivos
Econ. Jesús B. Zerpa
Directv 2020-Comité de Finanzas-
Vector Autorregresivo (Var)
Propuesta de modelo multivariante para el análisis macroeconómico de la inflación monetaria en Venezuela período 2015-2019. Análisis técnico realizado con las series históricas de cada variable (INPC, Base Monetaria, Tipo de Cambio) llevadas a números índice (Base 100 -2015-) y con aplicación logarítmica.
Dicho código fue realizado en el lenguaje de programación R para ser utilizado en RStudio o en herramientas avanzadas de Business Intelligence como Power BI. La prueba del modelo se realizó desde RMarkdown en RStudio.
Var.data <- read.csv("C:/Users/Personal/Desktop/Modelo en R/Modelo VAR/Var data.csv", sep=";")
Varcor<-Var.data
INPC<-Varcor[,1]
IBM<-Varcor[,2]
IDP<-Varcor[,3]
Var.lin<-data.frame(INPC,IBM,IDP)Matriz de correlación simple y aplicación de logaritmo
cor(Var.lin)## INPC IBM IDP
## INPC 1.0000000 0.9962789 0.9905231
## IBM 0.9962789 1.0000000 0.9856439
## IDP 0.9905231 0.9856439 1.0000000cor(log(Var.lin))## INPC IBM IDP
## INPC 1.0000000 0.9984334 0.9976446
## IBM 0.9984334 1.0000000 0.9946901
## IDP 0.9976446 0.9946901 1.0000000plot(log(Var.lin))
Correlación parcial
library(ggm)## Warning: package 'ggm' was built under R version 3.6.3parcor(cov(Var.lin))## INPC IBM IDP
## INPC 1.0000000 0.8614287 0.5873454
## IBM 0.8614287 1.0000000 -0.1008126
## IDP 0.5873454 -0.1008126 1.0000000Modelizacion del Vector autorregresivo multivariante Var(p):
Creación de series de tiempo y gráfica.
tinpc=ts(log(Var.lin[,1]), start=c(2015,12),end=c(2019,12),freq=12)
tibm=ts(log(Var.lin[,2]), start=c(2015,12),end=c(2019,12),freq=12)
timaxdp=ts(log(Var.lin[,3]), start=c(2015,12),end=c(2019,12),freq=12)
ts.plot(tinpc,tibm,timaxdp,col=c("blue", "red","black"), main="Log's del INPC, IBM e IDP en Venezuela 2015-2019",xlab="Años",ylab="Logaritmo")
bandas<-expression("INPC","Índice Base Monetaria ","Índice Dólar Paralelo")
legend(2016,10,bandas,lty=1,col=c("blue","red","black"),cex=.8)
Pruebas de hipótesis de Dickey Fuller al Índice de Precios al Consumidor (INPC).
library(vars)## Loading required package: MASS## Loading required package: strucchange## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric## Loading required package: sandwich## Loading required package: urca## Loading required package: lmtestadf1_ltip<-summary(ur.df(tinpc, lags=1))
adf1_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.17774 -0.08581 -0.04155 0.02948 0.33063
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 0.015511 0.004963 3.125 0.00311 **
## z.diff.lag 0.622931 0.130525 4.772 1.95e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1175 on 45 degrees of freedom
## Multiple R-squared: 0.8845, Adjusted R-squared: 0.8794
## F-statistic: 172.4 on 2 and 45 DF, p-value: < 2.2e-16
##
##
## Value of test-statistic is: 3.125
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltip<-summary(ur.df(tinpc, type="drift", lags=12))
adf2_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.15842 -0.05021 -0.01037 0.04089 0.21420
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.28492 0.40407 -0.705 0.4881
## z.lag.1 0.07144 0.09469 0.755 0.4585
## z.diff.lag1 0.35843 0.27168 1.319 0.2006
## z.diff.lag2 -0.13694 0.22618 -0.605 0.5511
## z.diff.lag3 -0.28656 0.24234 -1.182 0.2496
## z.diff.lag4 -0.19422 0.26517 -0.732 0.4716
## z.diff.lag5 0.32148 0.27191 1.182 0.2497
## z.diff.lag6 -0.14093 0.22866 -0.616 0.5440
## z.diff.lag7 -0.42747 0.21775 -1.963 0.0624 .
## z.diff.lag8 0.28949 0.29083 0.995 0.3304
## z.diff.lag9 -0.15696 0.26843 -0.585 0.5647
## z.diff.lag10 0.24084 0.24977 0.964 0.3454
## z.diff.lag11 -0.52776 0.24579 -2.147 0.0431 *
## z.diff.lag12 0.61485 0.28551 2.154 0.0425 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09227 on 22 degrees of freedom
## Multiple R-squared: 0.9023, Adjusted R-squared: 0.8446
## F-statistic: 15.64 on 13 and 22 DF, p-value: 3.432e-08
##
##
## Value of test-statistic is: 0.7545 0.54
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltip<-summary(ur.df(tinpc, type="trend", lags=1))
adf3_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.18996 -0.04537 -0.01993 0.02950 0.34793
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.219658 0.058765 -3.738 0.000543 ***
## z.lag.1 0.048186 0.015594 3.090 0.003504 **
## tt 0.002539 0.002873 0.884 0.381851
## z.diff.lag 0.142487 0.160767 0.886 0.380388
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1012 on 43 degrees of freedom
## Multiple R-squared: 0.8226, Adjusted R-squared: 0.8103
## F-statistic: 66.48 on 3 and 43 DF, p-value: 3.441e-16
##
##
## Value of test-statistic is: 3.09 10.2689 13.8257
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Primera diferencia REGULAR del logaritmo del Índice de precios INPC.
ten<-diff(tinpc,lag=1,difference=1)
ten## Jan Feb Mar Apr May Jun
## 2016 0.069805874 0.004837669 0.021575315 0.056502229 0.104553323 0.006934306
## 2017 0.037460805 0.014572122 0.009536668 0.100057130 0.071890121 0.081402619
## 2018 0.091161863 0.058269130 0.133888495 0.217536463 0.185859924 0.266832011
## 2019 0.340593755 0.401124048 0.467381404 0.455463239 0.309372780 0.700741969
## Jul Aug Sep Oct Nov Dec
## 2016 0.013801736 0.013763238 0.107337944 0.232957697 0.054204281 0.027068276
## 2017 0.075570623 0.135845753 0.161751520 0.346865849 0.149999197 0.152760632
## 2018 0.122223510 0.269757097 0.324760804 0.662086424 0.425640736 0.335392341
## 2019 0.583862268 0.745046055 0.499693632 0.509963938 0.739274057 0.838453380layout(matrix(c(1,1,2,3),2,2,byrow=TRUE))
ts.plot(ten,main="Primera diferencia Regular del Log INPC en Venezuela",xlab="año",ylab="")
acf(ten,main="Autocorrelación simple",ci.col="blue",ylab="",ylim=c(-.5,.5),lag.max=100)
pacf(ten,main="Autocorrelación parcial",ci.col="red",ylab="",ylim=c(-.5,.5),lag.max=100)
Aplicación de pruebas para determinar el nivel de estacionariedad.
adf1_ltip<-summary(ur.df(ten, lags=1))
adf1_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.22013 -0.06547 -0.00236 0.08376 0.34276
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 0.04503 0.06053 0.744 0.4609
## z.diff.lag -0.36463 0.15153 -2.406 0.0204 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1228 on 44 degrees of freedom
## Multiple R-squared: 0.1164, Adjusted R-squared: 0.07628
## F-statistic: 2.899 on 2 and 44 DF, p-value: 0.06564
##
##
## Value of test-statistic is: 0.7439
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltip<-summary(ur.df(ten, type="drift", lags=12))
adf2_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.179246 -0.050516 0.006357 0.040489 0.197650
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.02165 0.02819 0.768 0.45112
## z.lag.1 0.30982 0.16917 1.831 0.08127 .
## z.diff.lag1 -0.67271 0.33074 -2.034 0.05479 .
## z.diff.lag2 -0.79810 0.30690 -2.601 0.01670 *
## z.diff.lag3 -0.88907 0.33281 -2.671 0.01429 *
## z.diff.lag4 -0.93335 0.36159 -2.581 0.01742 *
## z.diff.lag5 -0.42638 0.38699 -1.102 0.28302
## z.diff.lag6 -0.53521 0.33223 -1.611 0.12212
## z.diff.lag7 -0.89990 0.33117 -2.717 0.01290 *
## z.diff.lag8 -0.38345 0.36415 -1.053 0.30431
## z.diff.lag9 -0.46858 0.30797 -1.522 0.14305
## z.diff.lag10 -0.16005 0.27703 -0.578 0.56958
## z.diff.lag11 -0.68013 0.23301 -2.919 0.00821 **
## z.diff.lag12 0.23526 0.25895 0.908 0.37392
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09283 on 21 degrees of freedom
## Multiple R-squared: 0.7268, Adjusted R-squared: 0.5577
## F-statistic: 4.298 on 13 and 21 DF, p-value: 0.001542
##
##
## Value of test-statistic is: 1.8314 3.0204
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltip<-summary(ur.df(ten, type="trend", lags=1))
adf3_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.18486 -0.06602 -0.01148 0.03134 0.29958
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.059961 0.039086 -1.534 0.13250
## z.lag.1 -0.509750 0.180742 -2.820 0.00729 **
## tt 0.008143 0.002712 3.003 0.00449 **
## z.diff.lag -0.099675 0.161346 -0.618 0.54006
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1126 on 42 degrees of freedom
## Multiple R-squared: 0.2773, Adjusted R-squared: 0.2257
## F-statistic: 5.372 on 3 and 42 DF, p-value: 0.003196
##
##
## Value of test-statistic is: -2.8203 3.6867 4.5687
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Segunda diferencia REGULAR.
ten3<-diff(ten,lag=1,difference=1)
ten3## Jan Feb Mar Apr May
## 2016 -6.496821e-02 1.673765e-02 3.492691e-02 4.805109e-02
## 2017 1.039253e-02 -2.288868e-02 -5.035454e-03 9.052046e-02 -2.816701e-02
## 2018 -6.159877e-02 -3.289273e-02 7.561937e-02 8.364797e-02 -3.167654e-02
## 2019 5.201414e-03 6.053029e-02 6.625736e-02 -1.191817e-02 -1.460905e-01
## Jun Jul Aug Sep Oct
## 2016 -9.761902e-02 6.867430e-03 -3.849889e-05 9.357471e-02 1.256198e-01
## 2017 9.512498e-03 -5.831996e-03 6.027513e-02 2.590577e-02 1.851143e-01
## 2018 8.097209e-02 -1.446085e-01 1.475336e-01 5.500371e-02 3.373256e-01
## 2019 3.913692e-01 -1.168797e-01 1.611838e-01 -2.453524e-01 1.027031e-02
## Nov Dec
## 2016 -1.787534e-01 -2.713600e-02
## 2017 -1.968667e-01 2.761435e-03
## 2018 -2.364457e-01 -9.024840e-02
## 2019 2.293101e-01 9.917932e-02layout(matrix(c(1,1,2,3),2,2,byrow=TRUE))
ts.plot(ten3,main="Segunda Diferencia Regular del log del INPC en Venezuela",xlab="año",ylab="")
acf(ten3,main="Autocorrelación simple",ci.col="blue",ylab="",ylim=c(-.5,.5),lag.max=100)
pacf(ten3,main="Autocorrelación parcial",ci.col="red",ylab="",ylim=c(-.5,.5),lag.max=100)
Aplicación de Dickey Fuller.
adf1_ltip<-summary(ur.df(ten3, lags=1))
adf1_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.19754 -0.05454 0.00680 0.08817 0.36874
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 -1.43558 0.26251 -5.469 2.15e-06 ***
## z.diff.lag 0.08056 0.16122 0.500 0.62
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1247 on 43 degrees of freedom
## Multiple R-squared: 0.6618, Adjusted R-squared: 0.6461
## F-statistic: 42.08 on 2 and 43 DF, p-value: 7.521e-11
##
##
## Value of test-statistic is: -5.4686
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltip<-summary(ur.df(ten3, type="drift", lags=12))
adf2_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.150595 -0.063221 0.001033 0.051496 0.189307
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.04683 0.02994 1.564 0.134
## z.lag.1 -2.65037 1.88425 -1.407 0.175
## z.diff.lag1 1.44812 1.82084 0.795 0.436
## z.diff.lag2 1.09227 1.71415 0.637 0.531
## z.diff.lag3 0.66798 1.61252 0.414 0.683
## z.diff.lag4 0.27861 1.49766 0.186 0.854
## z.diff.lag5 0.41564 1.36057 0.305 0.763
## z.diff.lag6 0.34767 1.20626 0.288 0.776
## z.diff.lag7 -0.12822 1.07059 -0.120 0.906
## z.diff.lag8 -0.05399 0.90731 -0.060 0.953
## z.diff.lag9 -0.14925 0.70665 -0.211 0.835
## z.diff.lag10 -0.01472 0.53611 -0.027 0.978
## z.diff.lag11 -0.48267 0.37548 -1.285 0.213
## z.diff.lag12 -0.02683 0.27094 -0.099 0.922
##
## Residual standard error: 0.1015 on 20 degrees of freedom
## Multiple R-squared: 0.8865, Adjusted R-squared: 0.8128
## F-statistic: 12.02 on 13 and 20 DF, p-value: 9.661e-07
##
##
## Value of test-statistic is: -1.4066 1.2527
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltip<-summary(ur.df(ten3, type="trend", lags=1))
adf3_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.24778 -0.08378 -0.00913 0.06367 0.34045
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.009011 0.038645 -0.233 0.817
## z.lag.1 -1.533355 0.265997 -5.765 9.35e-07 ***
## tt 0.001461 0.001426 1.024 0.312
## z.diff.lag 0.124442 0.161585 0.770 0.446
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1234 on 41 degrees of freedom
## Multiple R-squared: 0.6843, Adjusted R-squared: 0.6612
## F-statistic: 29.63 on 3 and 41 DF, p-value: 2.361e-10
##
##
## Value of test-statistic is: -5.7646 11.1569 16.6801
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Aplicación de pruebas para el índice de la Base Monetaria.
adf1_ltibm<-summary(ur.df(tibm, lags=1))
adf1_ltibm##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.20491 -0.05278 -0.02136 0.00146 0.36966
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 0.007681 0.004241 1.811 0.0768 .
## z.diff.lag 0.883964 0.107848 8.196 1.79e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09987 on 45 degrees of freedom
## Multiple R-squared: 0.9315, Adjusted R-squared: 0.9284
## F-statistic: 305.9 on 2 and 45 DF, p-value: < 2.2e-16
##
##
## Value of test-statistic is: 1.8111
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltibm<-summary(ur.df(tibm, type="drift", lags=12))
adf2_ltibm##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.105203 -0.025630 -0.003817 0.039713 0.116176
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.2005137 0.1139912 -1.759 0.092476 .
## z.lag.1 0.0463197 0.0228398 2.028 0.054838 .
## z.diff.lag1 0.8168759 0.2181718 3.744 0.001123 **
## z.diff.lag2 -0.1611196 0.2793431 -0.577 0.569943
## z.diff.lag3 -0.8003184 0.2962033 -2.702 0.013022 *
## z.diff.lag4 1.4555967 0.3758122 3.873 0.000821 ***
## z.diff.lag5 -0.9641344 0.4971157 -1.939 0.065375 .
## z.diff.lag6 0.2543001 0.5234564 0.486 0.631906
## z.diff.lag7 -0.0008826 0.5343894 -0.002 0.998697
## z.diff.lag8 0.6235829 0.5409468 1.153 0.261380
## z.diff.lag9 -1.4356544 0.5929135 -2.421 0.024159 *
## z.diff.lag10 0.9036597 0.7100823 1.273 0.216441
## z.diff.lag11 -0.0013671 0.7122832 -0.002 0.998486
## z.diff.lag12 -0.6212151 0.4644659 -1.337 0.194729
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.06329 on 22 degrees of freedom
## Multiple R-squared: 0.9664, Adjusted R-squared: 0.9465
## F-statistic: 48.61 on 13 and 22 DF, p-value: 3.921e-13
##
##
## Value of test-statistic is: 2.028 2.9118
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltibm<-summary(ur.df(tibm, type="trend", lags=1))
adf3_ltibm##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.226649 -0.056102 0.002263 0.030275 0.266949
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.274232 0.066482 -4.125 0.000167 ***
## z.lag.1 0.067678 0.017084 3.962 0.000276 ***
## tt -0.003040 0.002415 -1.259 0.214921
## z.diff.lag 0.317315 0.164710 1.927 0.060667 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.08621 on 43 degrees of freedom
## Multiple R-squared: 0.8966, Adjusted R-squared: 0.8894
## F-statistic: 124.3 on 3 and 43 DF, p-value: < 2.2e-16
##
##
## Value of test-statistic is: 3.9616 7.2652 10.613
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Primera Diferencia REGULAR.
ten4<-diff(tibm,lag=1,difference=1)
ten4## Jan Feb Mar Apr May Jun
## 2016 0.04774200 0.05246526 0.06165645 0.07683818 0.09369061 0.10230774
## 2017 0.08360494 0.10014960 0.13441501 0.16952133 0.17563952 0.08350317
## 2018 0.11965284 0.09865954 0.07932219 0.11060496 0.11642194 0.12828109
## 2019 0.36929184 0.34316448 0.44342209 0.74344590 0.67651467 0.59549579
## Jul Aug Sep Oct Nov Dec
## 2016 0.11688338 0.10924696 0.10770233 0.10551816 0.08372704 0.08866331
## 2017 0.06903614 0.08844441 0.07701106 0.10943665 0.14063823 0.16189345
## 2018 0.17436736 0.23158471 0.27705126 0.32459447 0.44206693 0.50689054
## 2019 0.56540473 0.82303005 0.63179292 0.80282636 0.67007301 1.08732213layout(matrix(c(1,1,2,3),2,2,byrow=TRUE))
ts.plot(ten4,main="Primera diferencia Regular del Log del IBM",xlab="año",ylab="")
acf(ten4,main="Autocorrelación simple",lag.max=100)
pacf(ten4,main="Autocorrelación parcial",ci.col="red",ylab="",ylim=c(-.5,.5),lag.max=100)
Dickey Fuller.
adf1_ltibm<-summary(ur.df(ten4, lags=1))
adf1_ltibm##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.184129 -0.029305 0.007436 0.036043 0.307733
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 0.10073 0.04299 2.343 0.02371 *
## z.diff.lag -0.52241 0.17373 -3.007 0.00435 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09529 on 44 degrees of freedom
## Multiple R-squared: 0.2056, Adjusted R-squared: 0.1695
## F-statistic: 5.695 on 2 and 44 DF, p-value: 0.006317
##
##
## Value of test-statistic is: 2.343
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltibm<-summary(ur.df(ten4, type="drift", lags=12))
adf2_ltibm##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.103682 -0.026350 -0.002322 0.021694 0.125461
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.05540 0.02574 2.153 0.04313 *
## z.lag.1 -0.40053 0.21770 -1.840 0.07997 .
## z.diff.lag1 0.37569 0.28792 1.305 0.20606
## z.diff.lag2 0.25660 0.31628 0.811 0.42629
## z.diff.lag3 -0.39314 0.29773 -1.320 0.20089
## z.diff.lag4 1.18352 0.38147 3.102 0.00539 **
## z.diff.lag5 0.10249 0.42862 0.239 0.81333
## z.diff.lag6 0.73869 0.43335 1.705 0.10302
## z.diff.lag7 0.58712 0.44898 1.308 0.20512
## z.diff.lag8 1.25587 0.46020 2.729 0.01257 *
## z.diff.lag9 -0.20946 0.46654 -0.449 0.65806
## z.diff.lag10 0.88728 0.49348 1.798 0.08657 .
## z.diff.lag11 0.29487 0.46480 0.634 0.53267
## z.diff.lag12 1.03409 0.57007 1.814 0.08400 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.065 on 21 degrees of freedom
## Multiple R-squared: 0.8123, Adjusted R-squared: 0.6961
## F-statistic: 6.989 on 13 and 21 DF, p-value: 5.136e-05
##
##
## Value of test-statistic is: -1.8398 2.328
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltibm<-summary(ur.df(ten4, type="trend", lags=1))
adf3_ltibm##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.160023 -0.035733 0.005768 0.032851 0.289496
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.027849 0.031297 -0.890 0.3786
## z.lag.1 -0.072111 0.115357 -0.625 0.5353
## tt 0.003053 0.001930 1.582 0.1212
## z.diff.lag -0.455286 0.177239 -2.569 0.0138 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09455 on 42 degrees of freedom
## Multiple R-squared: 0.2172, Adjusted R-squared: 0.1613
## F-statistic: 3.884 on 3 and 42 DF, p-value: 0.01544
##
##
## Value of test-statistic is: -0.6251 2.7548 2.0683
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Segunda diferencia REGULAR.
ten5<-diff(ten4,lag=1,difference=1)
ten5## Jan Feb Mar Apr May
## 2016 0.004723268 0.009191190 0.015181721 0.016852432
## 2017 -0.005058374 0.016544660 0.034265416 0.035106320 0.006118181
## 2018 -0.042240617 -0.020993300 -0.019337345 0.031282766 0.005816987
## 2019 -0.137598699 -0.026127356 0.100257611 0.300023813 -0.066931238
## Jun Jul Aug Sep Oct
## 2016 0.008617129 0.014575647 -0.007636420 -0.001544634 -0.002184170
## 2017 -0.092136344 -0.014467033 0.019408271 -0.011433347 0.032425589
## 2018 0.011859142 0.046086278 0.057217343 0.045466551 0.047543207
## 2019 -0.081018872 -0.030091068 0.257625327 -0.191237136 0.171033439
## Nov Dec
## 2016 -0.021791120 0.004936273
## 2017 0.031201583 0.021255219
## 2018 0.117472462 0.064823608
## 2019 -0.132753348 0.417249120layout(matrix(c(1,1,2,3),2,2,byrow=TRUE))
ts.plot(ten5,main="Segunda Diferencia Regular del log del IBM",xlab="año",ylab="")
acf(ten5,main="Autocorrelación simple",lag.max=100)
pacf(ten5,main="Autocorrelación parcial",ci.col="red",ylab="",ylim=c(-.5,.5),lag.max=100)
Pruebas:
adf1_ltip<-summary(ur.df(ten5, lags=1))
adf1_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.14316 -0.02199 0.01572 0.04590 0.34638
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 -1.2512 0.2921 -4.284 0.000101 ***
## z.diff.lag -0.1235 0.1879 -0.657 0.514382
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1017 on 43 degrees of freedom
## Multiple R-squared: 0.5946, Adjusted R-squared: 0.5758
## F-statistic: 31.54 on 2 and 43 DF, p-value: 3.703e-09
##
##
## Value of test-statistic is: -4.2838
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltip<-summary(ur.df(ten5, type="drift", lags=12))
adf2_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.093982 -0.025862 -0.004047 0.018622 0.142221
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.01749 0.01556 1.124 0.2744
## z.lag.1 -0.82155 0.72074 -1.140 0.2678
## z.diff.lag1 -0.09378 0.73508 -0.128 0.8998
## z.diff.lag2 -0.23447 0.74801 -0.313 0.7572
## z.diff.lag3 -0.99578 0.73969 -1.346 0.1933
## z.diff.lag4 -0.19246 0.81199 -0.237 0.8150
## z.diff.lag5 -0.60706 0.80363 -0.755 0.4588
## z.diff.lag6 -0.25958 0.80583 -0.322 0.7507
## z.diff.lag7 -0.30054 0.77654 -0.387 0.7028
## z.diff.lag8 0.44078 0.75826 0.581 0.5675
## z.diff.lag9 -0.24445 0.64524 -0.379 0.7088
## z.diff.lag10 0.26283 0.58449 0.450 0.6578
## z.diff.lag11 0.10941 0.47844 0.229 0.8214
## z.diff.lag12 0.89945 0.47609 1.889 0.0734 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.06598 on 20 degrees of freedom
## Multiple R-squared: 0.9201, Adjusted R-squared: 0.8682
## F-statistic: 17.72 on 13 and 20 DF, p-value: 3.472e-08
##
##
## Value of test-statistic is: -1.1399 0.7962
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltip<-summary(ur.df(ten5, type="trend", lags=1))
adf3_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.167459 -0.023043 0.008974 0.030716 0.288431
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.022012 0.030129 -0.731 0.4692
## z.lag.1 -1.545824 0.296672 -5.211 5.68e-06 ***
## tt 0.002184 0.001134 1.926 0.0611 .
## z.diff.lag 0.042115 0.187652 0.224 0.8235
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09597 on 41 degrees of freedom
## Multiple R-squared: 0.6547, Adjusted R-squared: 0.6294
## F-statistic: 25.91 on 3 and 41 DF, p-value: 1.457e-09
##
##
## Value of test-statistic is: -5.2106 9.2992 13.8378
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Aplicación de pruebas para el índice de Precios del Dólar Paralelo (Dólartoday).
adf1_ltimaxdp<-summary(ur.df(timaxdp, lags=1))
adf1_ltimaxdp##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4923 -0.2680 -0.0871 0.1420 0.8793
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 0.043155 0.007269 5.937 3.88e-07 ***
## z.diff.lag -0.184301 0.160470 -1.149 0.257
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3179 on 45 degrees of freedom
## Multiple R-squared: 0.5701, Adjusted R-squared: 0.551
## F-statistic: 29.83 on 2 and 45 DF, p-value: 5.641e-09
##
##
## Value of test-statistic is: 5.9368
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltimaxdp<-summary(ur.df(timaxdp, type="drift", lags=12))
adf2_ltimaxdp##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.36318 -0.23433 -0.05626 0.17632 0.88273
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.6412 0.5148 -1.246 0.226
## z.lag.1 0.1407 0.1018 1.382 0.181
## z.diff.lag1 -0.3399 0.2615 -1.300 0.207
## z.diff.lag2 -0.1103 0.2735 -0.403 0.691
## z.diff.lag3 -0.2898 0.2746 -1.055 0.303
## z.diff.lag4 -0.3165 0.2814 -1.124 0.273
## z.diff.lag5 -0.1506 0.2919 -0.516 0.611
## z.diff.lag6 -0.2232 0.2869 -0.778 0.445
## z.diff.lag7 -0.0105 0.3001 -0.035 0.972
## z.diff.lag8 -0.1590 0.2787 -0.571 0.574
## z.diff.lag9 0.1974 0.2521 0.783 0.442
## z.diff.lag10 -0.1115 0.2543 -0.438 0.665
## z.diff.lag11 -0.1241 0.2705 -0.459 0.651
## z.diff.lag12 0.1751 0.2859 0.612 0.547
##
## Residual standard error: 0.3664 on 22 degrees of freedom
## Multiple R-squared: 0.4933, Adjusted R-squared: 0.1939
## F-statistic: 1.648 on 13 and 22 DF, p-value: 0.146
##
##
## Value of test-statistic is: 1.3818 1.0792
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_timaxdp<-summary(ur.df(timaxdp, type="trend", lags=1))
adf3_timaxdp##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5099 -0.1979 -0.0120 0.1614 0.9695
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.251034 0.137828 -1.821 0.0755 .
## z.lag.1 0.061534 0.035732 1.722 0.0922 .
## tt 0.003012 0.009003 0.335 0.7396
## z.diff.lag -0.268990 0.161454 -1.666 0.1030
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3083 on 43 degrees of freedom
## Multiple R-squared: 0.3611, Adjusted R-squared: 0.3166
## F-statistic: 8.103 on 3 and 43 DF, p-value: 0.0002175
##
##
## Value of test-statistic is: 1.7221 14.1091 11.4526
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Primnera diferencia REGULAR
ten7<-diff(timaxdp,lag=1,difference=1)
ten7## Jan Feb Mar Apr May Jun
## 2016 0.15691828 0.12856137 0.10025883 0.36534737 0.18559558 0.33599621
## 2017 0.10185301 0.07331491 -0.04998094 -0.09179806 0.02531268 -0.03698567
## 2018 0.19982174 -0.13278301 0.12211795 0.35506289 0.24192205 0.36298007
## 2019 -0.09387410 0.09479015 0.96830927 0.70170838 0.99937891 0.05148103
## Jul Aug Sep Oct Nov Dec
## 2016 0.02980024 0.16435907 -0.04623778 0.12857906 -0.06998568 0.16632654
## 2017 0.02271319 0.04698542 0.33082746 1.10634747 -0.36052786 0.11347651
## 2018 0.46064714 0.49701589 0.34599275 0.85838193 0.13655042 0.74966211
## 2019 0.88890205 0.11714587 0.89000497 0.53113805 0.58671917 1.31325652layout(matrix(c(1,1,2,3),2,2,byrow=TRUE))
ts.plot(ten7,main="Primera diferencia Regular del Log del IDP",xlab="año",ylab="")
acf(ten7,main="Autocorrelación simple",lag.max=100)
pacf(ten7,main="Autocorrelación parcial",ci.col="red",ylab="",ylim=c(-.5,.5),lag.max=100)
#### Dickey Fuller:
adf1_ltimaxdp<-summary(ur.df(ten7, lags=1))
adf1_ltimaxdp##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.85176 -0.10055 0.05416 0.24264 0.99687
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 -0.1508 0.1451 -1.040 0.304239
## z.diff.lag -0.5780 0.1396 -4.141 0.000154 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3641 on 44 degrees of freedom
## Multiple R-squared: 0.422, Adjusted R-squared: 0.3957
## F-statistic: 16.06 on 2 and 44 DF, p-value: 5.789e-06
##
##
## Value of test-statistic is: -1.0395
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltimaxdp<-summary(ur.df(ten7, type="drift", lags=12))
adf2_ltimaxdp##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5123 -0.1847 -0.0308 0.1962 0.9761
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.07682 0.11525 0.667 0.5123
## z.lag.1 0.20291 0.44276 0.458 0.6515
## z.diff.lag1 -1.27693 0.51450 -2.482 0.0216 *
## z.diff.lag2 -1.14461 0.57303 -1.997 0.0589 .
## z.diff.lag3 -1.17977 0.60699 -1.944 0.0655 .
## z.diff.lag4 -1.19034 0.63642 -1.870 0.0754 .
## z.diff.lag5 -1.03470 0.65030 -1.591 0.1265
## z.diff.lag6 -0.96371 0.64256 -1.500 0.1486
## z.diff.lag7 -0.63644 0.62562 -1.017 0.3206
## z.diff.lag8 -0.55488 0.57314 -0.968 0.3440
## z.diff.lag9 -0.18764 0.51706 -0.363 0.7203
## z.diff.lag10 -0.19757 0.46493 -0.425 0.6752
## z.diff.lag11 -0.12871 0.39725 -0.324 0.7491
## z.diff.lag12 0.21498 0.28131 0.764 0.4532
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3812 on 21 degrees of freedom
## Multiple R-squared: 0.6834, Adjusted R-squared: 0.4874
## F-statistic: 3.487 on 13 and 21 DF, p-value: 0.005415
##
##
## Value of test-statistic is: 0.4583 1.2425
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_timaxdp<-summary(ur.df(ten7, type="trend", lags=1))
adf3_timaxdp##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.53637 -0.19521 0.00381 0.15685 0.90219
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.073572 0.098563 -0.746 0.459561
## z.lag.1 -1.002397 0.248298 -4.037 0.000225 ***
## tt 0.015414 0.004705 3.276 0.002114 **
## z.diff.lag -0.159104 0.160757 -0.990 0.327981
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3172 on 42 degrees of freedom
## Multiple R-squared: 0.58, Adjusted R-squared: 0.55
## F-statistic: 19.34 on 3 and 42 DF, p-value: 4.98e-08
##
##
## Value of test-statistic is: -4.0371 5.8021 8.4706
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Segunda Diferencia REGULAR.
ten8<-diff(ten7,lag=1,difference=1)
ten8## Jan Feb Mar Apr May Jun
## 2016 -0.02835690 -0.02830254 0.26508854 -0.17975179 0.15040064
## 2017 -0.06447353 -0.02853811 -0.12329585 -0.04181711 0.11711073 -0.06229835
## 2018 0.08634523 -0.33260476 0.25490097 0.23294494 -0.11314083 0.12105802
## 2019 -0.84353622 0.18866426 0.87351911 -0.26660089 0.29767053 -0.94789787
## Jul Aug Sep Oct Nov Dec
## 2016 -0.30619597 0.13455883 -0.21059685 0.17481684 -0.19856474 0.23631222
## 2017 0.05969886 0.02427223 0.28384204 0.77552000 -1.46687532 0.47400436
## 2018 0.09766707 0.03636875 -0.15102314 0.51238918 -0.72183151 0.61311169
## 2019 0.83742102 -0.77175618 0.77285909 -0.35886692 0.05558112 0.72653735layout(matrix(c(1,1,2,3),2,2,byrow=TRUE))
ts.plot(ten8,main="Segunda Diferencia Regular del log del IDP",xlab="año",ylab="")
acf(ten8,main="Autocorrelación simple",lag.max=100)
pacf(ten8,main="Autocorrelación parcial",ci.col="red",ylab="",ylim=c(-.5,.5),lag.max=100)
adf1_ltip<-summary(ur.df(ten8, lags=1))
adf1_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression none
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.77398 -0.11394 0.04363 0.16439 1.02633
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## z.lag.1 -2.1626 0.2799 -7.726 1.16e-09 ***
## z.diff.lag 0.3051 0.1536 1.986 0.0534 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3567 on 43 degrees of freedom
## Multiple R-squared: 0.8301, Adjusted R-squared: 0.8222
## F-statistic: 105 on 2 and 43 DF, p-value: < 2.2e-16
##
##
## Value of test-statistic is: -7.726
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau1 -2.62 -1.95 -1.61adf2_ltip<-summary(ur.df(ten8, type="drift", lags=12))
adf2_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression drift
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4415 -0.2346 -0.0095 0.2164 0.8998
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.13134 0.08275 1.587 0.1282
## z.lag.1 -8.34002 4.04591 -2.061 0.0525 .
## z.diff.lag1 6.28802 3.95867 1.588 0.1279
## z.diff.lag2 5.34677 3.77441 1.417 0.1720
## z.diff.lag3 4.35093 3.52426 1.235 0.2313
## z.diff.lag4 3.33699 3.21618 1.038 0.3119
## z.diff.lag5 2.43881 2.85299 0.855 0.4028
## z.diff.lag6 1.58855 2.46263 0.645 0.5262
## z.diff.lag7 1.03483 2.06323 0.502 0.6215
## z.diff.lag8 0.53354 1.67138 0.319 0.7529
## z.diff.lag9 0.37625 1.30007 0.289 0.7753
## z.diff.lag10 0.18879 0.94322 0.200 0.8434
## z.diff.lag11 0.02127 0.60094 0.035 0.9721
## z.diff.lag12 0.13947 0.27863 0.501 0.6222
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3886 on 20 degrees of freedom
## Multiple R-squared: 0.9016, Adjusted R-squared: 0.8376
## F-statistic: 14.1 on 13 and 20 DF, p-value: 2.527e-07
##
##
## Value of test-statistic is: -2.0613 2.2451
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau2 -3.58 -2.93 -2.60
## phi1 7.06 4.86 3.94adf3_ltip<-summary(ur.df(ten8, type="trend", lags=1))
adf3_ltip##
## ###############################################
## # Augmented Dickey-Fuller Test Unit Root Test #
## ###############################################
##
## Test regression trend
##
##
## Call:
## lm(formula = z.diff ~ z.lag.1 + 1 + tt + z.diff.lag)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.86048 -0.14850 0.02526 0.12098 1.00266
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.034292 0.113001 -0.303 0.7631
## z.lag.1 -2.179275 0.283582 -7.685 1.81e-09 ***
## tt 0.003028 0.004143 0.731 0.4690
## z.diff.lag 0.313307 0.155578 2.014 0.0506 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3608 on 41 degrees of freedom
## Multiple R-squared: 0.8342, Adjusted R-squared: 0.8221
## F-statistic: 68.77 on 3 and 41 DF, p-value: 4.778e-16
##
##
## Value of test-statistic is: -7.6848 19.7999 29.6425
##
## Critical values for test statistics:
## 1pct 5pct 10pct
## tau3 -4.15 -3.50 -3.18
## phi2 7.02 5.13 4.31
## phi3 9.31 6.73 5.61Gráficas en segundas diferencias de los índices.
ts.plot(ten3, ten5,ten8,col=c("blue", "red","black"), main="Gráfica de las Segundas Diferencias")
bandas<-expression("2DiffINPC","2DiffIBM","2DiffIDP")
legend(2016,-0.3,bandas,lty=1,col=c("blue","red","black"),cex=.9)
Pruebas de Causalidad en el sentido de Granger.
library(lmtest)INPC
grangertest(ten3~ten5, order=1)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:1) + Lags(ten5, 1:1)
## Model 2: ten3 ~ Lags(ten3, 1:1)
## Res.Df Df F Pr(>F)
## 1 43
## 2 44 -1 3.4676 0.06943 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten3~ten5, order=2)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:2) + Lags(ten5, 1:2)
## Model 2: ten3 ~ Lags(ten3, 1:2)
## Res.Df Df F Pr(>F)
## 1 40
## 2 42 -2 1.7418 0.1882grangertest(ten3~ten5, order=3)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:3) + Lags(ten5, 1:3)
## Model 2: ten3 ~ Lags(ten3, 1:3)
## Res.Df Df F Pr(>F)
## 1 37
## 2 40 -3 0.2776 0.8412grangertest(ten3~ten5, order=4)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:4) + Lags(ten5, 1:4)
## Model 2: ten3 ~ Lags(ten3, 1:4)
## Res.Df Df F Pr(>F)
## 1 34
## 2 38 -4 1.547 0.2108grangertest(ten3~ten5, order=5)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:5) + Lags(ten5, 1:5)
## Model 2: ten3 ~ Lags(ten3, 1:5)
## Res.Df Df F Pr(>F)
## 1 31
## 2 36 -5 1.403 0.2505grangertest(ten3~ten5, order=6)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:6) + Lags(ten5, 1:6)
## Model 2: ten3 ~ Lags(ten3, 1:6)
## Res.Df Df F Pr(>F)
## 1 28
## 2 34 -6 1.1949 0.3378grangertest(ten3~ten5, order=7)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:7) + Lags(ten5, 1:7)
## Model 2: ten3 ~ Lags(ten3, 1:7)
## Res.Df Df F Pr(>F)
## 1 25
## 2 32 -7 0.6968 0.6743grangertest(ten3~ten5, order=8)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:8) + Lags(ten5, 1:8)
## Model 2: ten3 ~ Lags(ten3, 1:8)
## Res.Df Df F Pr(>F)
## 1 22
## 2 30 -8 0.5119 0.8345grangertest(ten3~ten5, order=9)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:9) + Lags(ten5, 1:9)
## Model 2: ten3 ~ Lags(ten3, 1:9)
## Res.Df Df F Pr(>F)
## 1 19
## 2 28 -9 0.9422 0.5131grangertest(ten3~ten5, order=10)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:10) + Lags(ten5, 1:10)
## Model 2: ten3 ~ Lags(ten3, 1:10)
## Res.Df Df F Pr(>F)
## 1 16
## 2 26 -10 0.8812 0.5683grangertest(ten3~ten5, order=11)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:11) + Lags(ten5, 1:11)
## Model 2: ten3 ~ Lags(ten3, 1:11)
## Res.Df Df F Pr(>F)
## 1 13
## 2 24 -11 1.6962 0.1812grangertest(ten3~ten5, order=12)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:12) + Lags(ten5, 1:12)
## Model 2: ten3 ~ Lags(ten3, 1:12)
## Res.Df Df F Pr(>F)
## 1 10
## 2 22 -12 1.3874 0.3063Base Monetaria
grangertest(ten5~ten3, order=1)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:1) + Lags(ten3, 1:1)
## Model 2: ten5 ~ Lags(ten5, 1:1)
## Res.Df Df F Pr(>F)
## 1 43
## 2 44 -1 0.5615 0.4577grangertest(ten5~ten3, order=2)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:2) + Lags(ten3, 1:2)
## Model 2: ten5 ~ Lags(ten5, 1:2)
## Res.Df Df F Pr(>F)
## 1 40
## 2 42 -2 10.001 0.0003005 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=3)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:3) + Lags(ten3, 1:3)
## Model 2: ten5 ~ Lags(ten5, 1:3)
## Res.Df Df F Pr(>F)
## 1 37
## 2 40 -3 5.2643 0.003989 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=4)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:4) + Lags(ten3, 1:4)
## Model 2: ten5 ~ Lags(ten5, 1:4)
## Res.Df Df F Pr(>F)
## 1 34
## 2 38 -4 2.5149 0.05957 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=5)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:5) + Lags(ten3, 1:5)
## Model 2: ten5 ~ Lags(ten5, 1:5)
## Res.Df Df F Pr(>F)
## 1 31
## 2 36 -5 1.8773 0.127grangertest(ten5~ten3, order=6)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:6) + Lags(ten3, 1:6)
## Model 2: ten5 ~ Lags(ten5, 1:6)
## Res.Df Df F Pr(>F)
## 1 28
## 2 34 -6 2.6273 0.03787 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=7)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:7) + Lags(ten3, 1:7)
## Model 2: ten5 ~ Lags(ten5, 1:7)
## Res.Df Df F Pr(>F)
## 1 25
## 2 32 -7 3.564 0.00855 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=8)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:8) + Lags(ten3, 1:8)
## Model 2: ten5 ~ Lags(ten5, 1:8)
## Res.Df Df F Pr(>F)
## 1 22
## 2 30 -8 2.6424 0.03391 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=9)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:9) + Lags(ten3, 1:9)
## Model 2: ten5 ~ Lags(ten5, 1:9)
## Res.Df Df F Pr(>F)
## 1 19
## 2 28 -9 2.0051 0.09663 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=10)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:10) + Lags(ten3, 1:10)
## Model 2: ten5 ~ Lags(ten5, 1:10)
## Res.Df Df F Pr(>F)
## 1 16
## 2 26 -10 2.3144 0.06502 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten5~ten3, order=11)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:11) + Lags(ten3, 1:11)
## Model 2: ten5 ~ Lags(ten5, 1:11)
## Res.Df Df F Pr(>F)
## 1 13
## 2 24 -11 1.7956 0.157grangertest(ten5~ten3, order=12)## Granger causality test
##
## Model 1: ten5 ~ Lags(ten5, 1:12) + Lags(ten3, 1:12)
## Model 2: ten5 ~ Lags(ten5, 1:12)
## Res.Df Df F Pr(>F)
## 1 10
## 2 22 -12 1.3835 0.3079INPC Vs. Dólar Paralelo
grangertest(ten3~ten8, order=1)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:1) + Lags(ten8, 1:1)
## Model 2: ten3 ~ Lags(ten3, 1:1)
## Res.Df Df F Pr(>F)
## 1 43
## 2 44 -1 0.2855 0.5959grangertest(ten3~ten8, order=2)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:2) + Lags(ten8, 1:2)
## Model 2: ten3 ~ Lags(ten3, 1:2)
## Res.Df Df F Pr(>F)
## 1 40
## 2 42 -2 0.581 0.564grangertest(ten3~ten8, order=3)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:3) + Lags(ten8, 1:3)
## Model 2: ten3 ~ Lags(ten3, 1:3)
## Res.Df Df F Pr(>F)
## 1 37
## 2 40 -3 0.6153 0.6094grangertest(ten3~ten8, order=4)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:4) + Lags(ten8, 1:4)
## Model 2: ten3 ~ Lags(ten3, 1:4)
## Res.Df Df F Pr(>F)
## 1 34
## 2 38 -4 2.3361 0.07518 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten3~ten8, order=5)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:5) + Lags(ten8, 1:5)
## Model 2: ten3 ~ Lags(ten3, 1:5)
## Res.Df Df F Pr(>F)
## 1 31
## 2 36 -5 2.001 0.1062grangertest(ten3~ten8, order=6)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:6) + Lags(ten8, 1:6)
## Model 2: ten3 ~ Lags(ten3, 1:6)
## Res.Df Df F Pr(>F)
## 1 28
## 2 34 -6 1.9754 0.1032grangertest(ten3~ten8, order=7)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:7) + Lags(ten8, 1:7)
## Model 2: ten3 ~ Lags(ten3, 1:7)
## Res.Df Df F Pr(>F)
## 1 25
## 2 32 -7 1.0463 0.4253grangertest(ten3~ten8, order=8)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:8) + Lags(ten8, 1:8)
## Model 2: ten3 ~ Lags(ten3, 1:8)
## Res.Df Df F Pr(>F)
## 1 22
## 2 30 -8 0.9351 0.5082grangertest(ten3~ten8, order=9)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:9) + Lags(ten8, 1:9)
## Model 2: ten3 ~ Lags(ten3, 1:9)
## Res.Df Df F Pr(>F)
## 1 19
## 2 28 -9 0.9642 0.4974grangertest(ten3~ten8, order=10)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:10) + Lags(ten8, 1:10)
## Model 2: ten3 ~ Lags(ten3, 1:10)
## Res.Df Df F Pr(>F)
## 1 16
## 2 26 -10 0.9871 0.4912grangertest(ten3~ten8, order=11)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:11) + Lags(ten8, 1:11)
## Model 2: ten3 ~ Lags(ten3, 1:11)
## Res.Df Df F Pr(>F)
## 1 13
## 2 24 -11 0.9256 0.5455grangertest(ten3~ten8, order=12)## Granger causality test
##
## Model 1: ten3 ~ Lags(ten3, 1:12) + Lags(ten8, 1:12)
## Model 2: ten3 ~ Lags(ten3, 1:12)
## Res.Df Df F Pr(>F)
## 1 10
## 2 22 -12 1.5771 0.2392Se invierten valores.
grangertest(ten8~ten3, order=1)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:1) + Lags(ten3, 1:1)
## Model 2: ten8 ~ Lags(ten8, 1:1)
## Res.Df Df F Pr(>F)
## 1 43
## 2 44 -1 1.2992 0.2607grangertest(ten8~ten3, order=2)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:2) + Lags(ten3, 1:2)
## Model 2: ten8 ~ Lags(ten8, 1:2)
## Res.Df Df F Pr(>F)
## 1 40
## 2 42 -2 1.2955 0.285grangertest(ten8~ten3, order=3)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:3) + Lags(ten3, 1:3)
## Model 2: ten8 ~ Lags(ten8, 1:3)
## Res.Df Df F Pr(>F)
## 1 37
## 2 40 -3 0.9662 0.419grangertest(ten8~ten3, order=4)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:4) + Lags(ten3, 1:4)
## Model 2: ten8 ~ Lags(ten8, 1:4)
## Res.Df Df F Pr(>F)
## 1 34
## 2 38 -4 0.7439 0.5688grangertest(ten8~ten3, order=5)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:5) + Lags(ten3, 1:5)
## Model 2: ten8 ~ Lags(ten8, 1:5)
## Res.Df Df F Pr(>F)
## 1 31
## 2 36 -5 1.0424 0.4106grangertest(ten8~ten3, order=6)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:6) + Lags(ten3, 1:6)
## Model 2: ten8 ~ Lags(ten8, 1:6)
## Res.Df Df F Pr(>F)
## 1 28
## 2 34 -6 1.1629 0.3538grangertest(ten8~ten3, order=7)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:7) + Lags(ten3, 1:7)
## Model 2: ten8 ~ Lags(ten8, 1:7)
## Res.Df Df F Pr(>F)
## 1 25
## 2 32 -7 1.0115 0.447grangertest(ten8~ten3, order=8)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:8) + Lags(ten3, 1:8)
## Model 2: ten8 ~ Lags(ten8, 1:8)
## Res.Df Df F Pr(>F)
## 1 22
## 2 30 -8 0.7145 0.6766grangertest(ten8~ten3, order=9)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:9) + Lags(ten3, 1:9)
## Model 2: ten8 ~ Lags(ten8, 1:9)
## Res.Df Df F Pr(>F)
## 1 19
## 2 28 -9 0.6369 0.7524grangertest(ten8~ten3, order=10)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:10) + Lags(ten3, 1:10)
## Model 2: ten8 ~ Lags(ten8, 1:10)
## Res.Df Df F Pr(>F)
## 1 16
## 2 26 -10 0.8101 0.6235grangertest(ten8~ten3, order=11)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:11) + Lags(ten3, 1:11)
## Model 2: ten8 ~ Lags(ten8, 1:11)
## Res.Df Df F Pr(>F)
## 1 13
## 2 24 -11 0.7878 0.6499grangertest(ten8~ten3, order=12)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:12) + Lags(ten3, 1:12)
## Model 2: ten8 ~ Lags(ten8, 1:12)
## Res.Df Df F Pr(>F)
## 1 10
## 2 22 -12 1.0922 0.4508Dólar paralelo a través de la Base monetaria.
grangertest(ten8~ten3, order=1)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:1) + Lags(ten3, 1:1)
## Model 2: ten8 ~ Lags(ten8, 1:1)
## Res.Df Df F Pr(>F)
## 1 43
## 2 44 -1 1.2992 0.2607grangertest(ten8~ten3, order=2)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:2) + Lags(ten3, 1:2)
## Model 2: ten8 ~ Lags(ten8, 1:2)
## Res.Df Df F Pr(>F)
## 1 40
## 2 42 -2 1.2955 0.285grangertest(ten8~ten3, order=3)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:3) + Lags(ten3, 1:3)
## Model 2: ten8 ~ Lags(ten8, 1:3)
## Res.Df Df F Pr(>F)
## 1 37
## 2 40 -3 0.9662 0.419grangertest(ten8~ten3, order=4)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:4) + Lags(ten3, 1:4)
## Model 2: ten8 ~ Lags(ten8, 1:4)
## Res.Df Df F Pr(>F)
## 1 34
## 2 38 -4 0.7439 0.5688grangertest(ten8~ten3, order=5)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:5) + Lags(ten3, 1:5)
## Model 2: ten8 ~ Lags(ten8, 1:5)
## Res.Df Df F Pr(>F)
## 1 31
## 2 36 -5 1.0424 0.4106grangertest(ten8~ten3, order=6)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:6) + Lags(ten3, 1:6)
## Model 2: ten8 ~ Lags(ten8, 1:6)
## Res.Df Df F Pr(>F)
## 1 28
## 2 34 -6 1.1629 0.3538grangertest(ten8~ten3, order=7)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:7) + Lags(ten3, 1:7)
## Model 2: ten8 ~ Lags(ten8, 1:7)
## Res.Df Df F Pr(>F)
## 1 25
## 2 32 -7 1.0115 0.447grangertest(ten8~ten3, order=8)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:8) + Lags(ten3, 1:8)
## Model 2: ten8 ~ Lags(ten8, 1:8)
## Res.Df Df F Pr(>F)
## 1 22
## 2 30 -8 0.7145 0.6766grangertest(ten8~ten3, order=9)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:9) + Lags(ten3, 1:9)
## Model 2: ten8 ~ Lags(ten8, 1:9)
## Res.Df Df F Pr(>F)
## 1 19
## 2 28 -9 0.6369 0.7524grangertest(ten8~ten3, order=10)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:10) + Lags(ten3, 1:10)
## Model 2: ten8 ~ Lags(ten8, 1:10)
## Res.Df Df F Pr(>F)
## 1 16
## 2 26 -10 0.8101 0.6235grangertest(ten8~ten3, order=11)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:11) + Lags(ten3, 1:11)
## Model 2: ten8 ~ Lags(ten8, 1:11)
## Res.Df Df F Pr(>F)
## 1 13
## 2 24 -11 0.7878 0.6499grangertest(ten8~ten3, order=12)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:12) + Lags(ten3, 1:12)
## Model 2: ten8 ~ Lags(ten8, 1:12)
## Res.Df Df F Pr(>F)
## 1 10
## 2 22 -12 1.0922 0.4508Invertimos variables.
grangertest(ten8~ten5, order=1)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:1) + Lags(ten5, 1:1)
## Model 2: ten8 ~ Lags(ten8, 1:1)
## Res.Df Df F Pr(>F)
## 1 43
## 2 44 -1 0.0337 0.8552grangertest(ten8~ten5, order=2)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:2) + Lags(ten5, 1:2)
## Model 2: ten8 ~ Lags(ten8, 1:2)
## Res.Df Df F Pr(>F)
## 1 40
## 2 42 -2 1.2477 0.2981grangertest(ten8~ten5, order=3)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:3) + Lags(ten5, 1:3)
## Model 2: ten8 ~ Lags(ten8, 1:3)
## Res.Df Df F Pr(>F)
## 1 37
## 2 40 -3 2.8009 0.05331 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1grangertest(ten8~ten5, order=4)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:4) + Lags(ten5, 1:4)
## Model 2: ten8 ~ Lags(ten8, 1:4)
## Res.Df Df F Pr(>F)
## 1 34
## 2 38 -4 1.5524 0.2094grangertest(ten8~ten5, order=5)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:5) + Lags(ten5, 1:5)
## Model 2: ten8 ~ Lags(ten8, 1:5)
## Res.Df Df F Pr(>F)
## 1 31
## 2 36 -5 1.0679 0.397grangertest(ten8~ten5, order=6)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:6) + Lags(ten5, 1:6)
## Model 2: ten8 ~ Lags(ten8, 1:6)
## Res.Df Df F Pr(>F)
## 1 28
## 2 34 -6 1.0173 0.4344grangertest(ten8~ten5, order=7)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:7) + Lags(ten5, 1:7)
## Model 2: ten8 ~ Lags(ten8, 1:7)
## Res.Df Df F Pr(>F)
## 1 25
## 2 32 -7 0.9262 0.5036grangertest(ten8~ten5, order=8)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:8) + Lags(ten5, 1:8)
## Model 2: ten8 ~ Lags(ten8, 1:8)
## Res.Df Df F Pr(>F)
## 1 22
## 2 30 -8 1.5383 0.201grangertest(ten8~ten5, order=9)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:9) + Lags(ten5, 1:9)
## Model 2: ten8 ~ Lags(ten8, 1:9)
## Res.Df Df F Pr(>F)
## 1 19
## 2 28 -9 1.7783 0.1392grangertest(ten8~ten5, order=10)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:10) + Lags(ten5, 1:10)
## Model 2: ten8 ~ Lags(ten8, 1:10)
## Res.Df Df F Pr(>F)
## 1 16
## 2 26 -10 1.3075 0.3052grangertest(ten8~ten5, order=11)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:11) + Lags(ten5, 1:11)
## Model 2: ten8 ~ Lags(ten8, 1:11)
## Res.Df Df F Pr(>F)
## 1 13
## 2 24 -11 1.0793 0.4422grangertest(ten8~ten5, order=12)## Granger causality test
##
## Model 1: ten8 ~ Lags(ten8, 1:12) + Lags(ten5, 1:12)
## Model 2: ten8 ~ Lags(ten8, 1:12)
## Res.Df Df F Pr(>F)
## 1 10
## 2 22 -12 0.796 0.6509Elaboración del Vector Autorregresivo
model<-ts(Var.lin,start=2015,freq=12)
model1<-diff(diff(model))
var1<-VAR(model1,p=1)
var1##
## VAR Estimation Results:
## =======================
##
## Estimated coefficients for equation INPC:
## =========================================
## Call:
## INPC = INPC.l1 + IBM.l1 + IDP.l1 + const
##
## INPC.l1 IBM.l1 IDP.l1 const
## 8.390897e-01 -6.020032e-02 -4.382424e-02 8.261831e+05
##
##
## Estimated coefficients for equation IBM:
## ========================================
## Call:
## IBM = INPC.l1 + IBM.l1 + IDP.l1 + const
##
## INPC.l1 IBM.l1 IDP.l1 const
## 3.103139e-01 3.667736e-01 1.220480e-01 1.365071e+06
##
##
## Estimated coefficients for equation IDP:
## ========================================
## Call:
## IDP = INPC.l1 + IBM.l1 + IDP.l1 + const
##
## INPC.l1 IBM.l1 IDP.l1 const
## 2.235000e+01 -5.229013e+00 -1.083764e+00 7.674906e+06summary(var1)##
## VAR Estimation Results:
## =========================
## Endogenous variables: INPC, IBM, IDP
## Deterministic variables: const
## Sample size: 57
## Log Likelihood: -3037.75
## Roots of the characteristic polynomial:
## 0.9221 0.9221 0.5267
## Call:
## VAR(y = model1, p = 1)
##
##
## Estimation results for equation INPC:
## =====================================
## INPC = INPC.l1 + IBM.l1 + IDP.l1 + const
##
## Estimate Std. Error t value Pr(>|t|)
## INPC.l1 8.391e-01 1.130e-01 7.425 9.36e-10 ***
## IBM.l1 -6.020e-02 3.462e-02 -1.739 0.0879 .
## IDP.l1 -4.382e-02 4.686e-03 -9.353 8.28e-13 ***
## const 8.262e+05 6.622e+05 1.248 0.2177
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## Residual standard error: 4759000 on 53 degrees of freedom
## Multiple R-Squared: 0.6365, Adjusted R-squared: 0.6159
## F-statistic: 30.94 on 3 and 53 DF, p-value: 1.071e-11
##
##
## Estimation results for equation IBM:
## ====================================
## IBM = INPC.l1 + IBM.l1 + IDP.l1 + const
##
## Estimate Std. Error t value Pr(>|t|)
## INPC.l1 3.103e-01 1.748e-01 1.776 0.0815 .
## IBM.l1 3.668e-01 5.354e-02 6.851 7.85e-09 ***
## IDP.l1 1.220e-01 7.246e-03 16.844 < 2e-16 ***
## const 1.365e+06 1.024e+06 1.333 0.1882
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## Residual standard error: 7359000 on 53 degrees of freedom
## Multiple R-Squared: 0.9061, Adjusted R-squared: 0.9008
## F-statistic: 170.4 on 3 and 53 DF, p-value: < 2.2e-16
##
##
## Estimation results for equation IDP:
## ====================================
## IDP = INPC.l1 + IBM.l1 + IDP.l1 + const
##
## Estimate Std. Error t value Pr(>|t|)
## INPC.l1 2.235e+01 1.861e+00 12.009 < 2e-16 ***
## IBM.l1 -5.229e+00 5.701e-01 -9.171 1.58e-12 ***
## IDP.l1 -1.084e+00 7.716e-02 -14.045 < 2e-16 ***
## const 7.675e+06 1.091e+07 0.704 0.485
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
##
## Residual standard error: 78370000 on 53 degrees of freedom
## Multiple R-Squared: 0.8278, Adjusted R-squared: 0.8181
## F-statistic: 84.94 on 3 and 53 DF, p-value: < 2.2e-16
##
##
##
## Covariance matrix of residuals:
## INPC IBM IDP
## INPC 2.265e+13 1.858e+13 -2.401e+13
## IBM 1.858e+13 5.416e+13 1.315e+14
## IDP -2.401e+13 1.315e+14 6.142e+15
##
## Correlation matrix of residuals:
## INPC IBM IDP
## INPC 1.00000 0.5306 -0.06437
## IBM 0.53058 1.0000 0.22793
## IDP -0.06437 0.2279 1.00000plot(var1)
bv.serial <- serial.test(var1, lags.pt = 12, type = "PT.asymptotic")
bv.serial##
## Portmanteau Test (asymptotic)
##
## data: Residuals of VAR object var1
## Chi-squared = 193.19, df = 99, p-value = 4.748e-08Función de impulso respuesta acumulativa
var1_irflp<-irf(var1, response="INPC", n.ahead=40, cumulative=TRUE,boot=TRUE)
var1_irflp##
## Impulse response coefficients
## $INPC
## INPC
## [1,] 4759123
## [2,] 8738482
## [3,] 7933231
## [4,] 7430578
## [5,] 9664531
## [6,] 9896959
## [7,] 8276683
## [8,] 8931240
## [9,] 10147740
## [10,] 9153513
## [11,] 8550083
## [12,] 9654776
## [13,] 9728905
## [14,] 8763763
## [15,] 9093431
## [16,] 9781898
## [17,] 9223636
## [18,] 8864408
## [19,] 9484624
## [20,] 9539238
## [21,] 8989804
## [22,] 9165688
## [23,] 9561736
## [24,] 9251946
## [25,] 9040519
## [26,] 9389486
## [27,] 9428078
## [28,] 9115729
## [29,] 9209288
## [30,] 9437033
## [31,] 9265333
## [32,] 9141145
## [33,] 9337391
## [34,] 9363591
## [35,] 9186118
## [36,] 9235644
## [37,] 9366516
## [38,] 9271452
## [39,] 9198631
## [40,] 9308929
## [41,] 9326225
##
## $IBM
## INPC
## [1,] 0.00
## [2,] -1437492.68
## [3,] -379041.09
## [4,] 666204.31
## [5,] -524443.33
## [6,] -861840.12
## [7,] 323801.79
## [8,] 150321.44
## [9,] -777490.59
## [10,] -249226.47
## [11,] 328806.17
## [12,] -352771.67
## [13,] -567741.00
## [14,] 99209.68
## [15,] 12375.98
## [16,] -519501.88
## [17,] -230409.71
## [18,] 104925.85
## [19,] -276554.74
## [20,] -407345.04
## [21,] -30040.88
## [22,] -71479.49
## [23,] -375543.49
## [24,] -217283.81
## [25,] -22761.30
## [26,] -236036.06
## [27,] -315153.43
## [28,] -101790.06
## [29,] -120840.28
## [30,] -294560.83
## [31,] -208075.52
## [32,] -95348.11
## [33,] -214497.65
## [34,] -262145.29
## [35,] -141551.47
## [36,] -149827.13
## [37,] -249022.77
## [38,] -201851.73
## [39,] -136588.37
## [40,] -203104.29
## [41,] -231687.36
##
## $IDP
## INPC
## [1,] 0.0
## [2,] -3258767.6
## [3,] -3007776.3
## [4,] -900554.6
## [5,] -2262677.8
## [6,] -3659361.7
## [7,] -2018171.1
## [8,] -1537819.9
## [9,] -3150501.1
## [10,] -2918475.7
## [11,] -1647370.6
## [12,] -2362279.6
## [13,] -3155637.1
## [14,] -2227667.4
## [15,] -1928994.0
## [16,] -2839167.7
## [17,] -2725020.6
## [18,] -1997331.6
## [19,] -2388850.4
## [20,] -2849235.7
## [21,] -2330058.4
## [22,] -2148643.2
## [23,] -2663515.1
## [24,] -2609464.0
## [25,] -2193525.2
## [26,] -2407773.3
## [27,] -2674773.0
## [28,] -2384565.9
## [29,] -2274945.8
## [30,] -2566067.8
## [31,] -2541494.1
## [32,] -2303888.1
## [33,] -2420918.0
## [34,] -2575610.6
## [35,] -2413509.4
## [36,] -2347555.7
## [37,] -2512078.9
## [38,] -2501595.7
## [39,] -2365939.0
## [40,] -2429739.1
## [41,] -2519278.2
##
##
## Lower Band, CI= 0.95
## $INPC
## INPC
## [1,] 2699339
## [2,] 3931013
## [3,] 3251389
## [4,] 3561942
## [5,] 4819239
## [6,] 4338932
## [7,] 3418460
## [8,] 4550426
## [9,] 4752228
## [10,] 3893291
## [11,] 4115673
## [12,] 4717802
## [13,] 4326070
## [14,] 3820968
## [15,] 4549827
## [16,] 4603475
## [17,] 4074266
## [18,] 4321184
## [19,] 4608278
## [20,] 4340786
## [21,] 4135264
## [22,] 4520996
## [23,] 4516699
## [24,] 4233942
## [25,] 4438504
## [26,] 4549122
## [27,] 4375694
## [28,] 4350622
## [29,] 4523222
## [30,] 4473007
## [31,] 4357761
## [32,] 4474678
## [33,] 4517026
## [34,] 4408559
## [35,] 4453062
## [36,] 4513117
## [37,] 4459594
## [38,] 4425341
## [39,] 4494829
## [40,] 4494045
## [41,] 4433391
##
## $IBM
## INPC
## [1,] 0.0
## [2,] -4374097.7
## [3,] -2816985.5
## [4,] -243972.9
## [5,] -2885130.4
## [6,] -3888660.7
## [7,] -1508009.5
## [8,] -1532346.3
## [9,] -3770440.5
## [10,] -2761545.2
## [11,] -1109570.1
## [12,] -2971209.5
## [13,] -3099108.2
## [14,] -2065324.3
## [15,] -2106220.8
## [16,] -3119636.7
## [17,] -2555514.8
## [18,] -1742312.7
## [19,] -2831292.6
## [20,] -2676325.5
## [21,] -2154838.1
## [22,] -2310967.6
## [23,] -2639370.7
## [24,] -2414607.7
## [25,] -2041709.5
## [26,] -2621310.5
## [27,] -2406165.3
## [28,] -2147687.6
## [29,] -2349841.0
## [30,] -2405528.3
## [31,] -2302941.3
## [32,] -2157975.1
## [33,] -2420120.8
## [34,] -2280486.8
## [35,] -2227527.4
## [36,] -2327378.5
## [37,] -2286436.6
## [38,] -2262923.6
## [39,] -2224278.3
## [40,] -2318066.2
## [41,] -2228646.3
##
## $IDP
## INPC
## [1,] 0
## [2,] -4072489
## [3,] -3626020
## [4,] -1669359
## [5,] -3004896
## [6,] -4696401
## [7,] -2935907
## [8,] -2538596
## [9,] -4166709
## [10,] -3900764
## [11,] -2903144
## [12,] -3280686
## [13,] -4095320
## [14,] -3285097
## [15,] -2994383
## [16,] -3862612
## [17,] -3758564
## [18,] -3237023
## [19,] -3355517
## [20,] -3762453
## [21,] -3343133
## [22,] -3180356
## [23,] -3601023
## [24,] -3638677
## [25,] -3296403
## [26,] -3363986
## [27,] -3578408
## [28,] -3346365
## [29,] -3303388
## [30,] -3529669
## [31,] -3494913
## [32,] -3314554
## [33,] -3319992
## [34,] -3510106
## [35,] -3330174
## [36,] -3316314
## [37,] -3506522
## [38,] -3490227
## [39,] -3320782
## [40,] -3394609
## [41,] -3497416
##
##
## Upper Band, CI= 0.95
## $INPC
## INPC
## [1,] 5872626
## [2,] 11731373
## [3,] 11915280
## [4,] 11803996
## [5,] 14717781
## [6,] 15644579
## [7,] 14397060
## [8,] 14879705
## [9,] 16462063
## [10,] 15610604
## [11,] 15126644
## [12,] 16077407
## [13,] 16256790
## [14,] 15520929
## [15,] 15660615
## [16,] 16449937
## [17,] 15811716
## [18,] 15626994
## [19,] 16072417
## [20,] 16137579
## [21,] 15706006
## [22,] 15802943
## [23,] 16305389
## [24,] 15820374
## [25,] 15750908
## [26,] 16022377
## [27,] 16041156
## [28,] 15773540
## [29,] 15835018
## [30,] 16199944
## [31,] 15825365
## [32,] 15801656
## [33,] 15980191
## [34,] 15974613
## [35,] 15806928
## [36,] 15844881
## [37,] 16113401
## [38,] 15831223
## [39,] 15824814
## [40,] 15943454
## [41,] 15922963
##
## $IBM
## INPC
## [1,] 0
## [2,] 1152489
## [3,] 1583464
## [4,] 1350325
## [5,] 1217772
## [6,] 1747107
## [7,] 1776645
## [8,] 1337954
## [9,] 1690346
## [10,] 1779544
## [11,] 1747010
## [12,] 1450428
## [13,] 1737906
## [14,] 1859229
## [15,] 1437672
## [16,] 1625560
## [17,] 1684108
## [18,] 1713669
## [19,] 1495575
## [20,] 1633121
## [21,] 1790673
## [22,] 1491899
## [23,] 1583869
## [24,] 1617429
## [25,] 1679884
## [26,] 1503902
## [27,] 1584272
## [28,] 1721481
## [29,] 1512592
## [30,] 1551987
## [31,] 1584709
## [32,] 1640302
## [33,] 1520700
## [34,] 1566639
## [35,] 1663066
## [36,] 1519997
## [37,] 1548351
## [38,] 1561520
## [39,] 1600132
## [40,] 1531979
## [41,] 1555531
##
## $IDP
## INPC
## [1,] 0.00
## [2,] -897619.36
## [3,] -754063.60
## [4,] -49208.63
## [5,] -590662.45
## [6,] -955946.23
## [7,] -356977.23
## [8,] -372025.66
## [9,] -857399.40
## [10,] -676437.87
## [11,] -323375.24
## [12,] -627218.93
## [13,] -827723.61
## [14,] -422382.90
## [15,] -471612.71
## [16,] -780700.50
## [17,] -567540.62
## [18,] -465048.62
## [19,] -646659.41
## [20,] -748700.75
## [21,] -516118.05
## [22,] -518005.41
## [23,] -739227.75
## [24,] -543762.88
## [25,] -532277.80
## [26,] -658216.53
## [27,] -695726.13
## [28,] -567596.34
## [29,] -541853.67
## [30,] -720762.25
## [31,] -577878.12
## [32,] -552277.30
## [33,] -662628.47
## [34,] -658294.26
## [35,] -571737.07
## [36,] -559456.73
## [37,] -701430.21
## [38,] -575891.94
## [39,] -561994.10
## [40,] -661561.52
## [41,] -630984.03plot(var1_irflp)
Descomposición de la varianza
var1_fevd_d2lp<-fevd(var1, n.ahead=50)$INPC
var1_fevd_d2lp## INPC IBM IDP
## [1,] 1.0000000 0.00000000 0.0000000
## [2,] 0.7520847 0.04038235 0.2075330
## [3,] 0.7383268 0.06012396 0.2015493
## [4,] 0.6699625 0.07279131 0.2572462
## [5,] 0.6618234 0.08496296 0.2532136
## [6,] 0.6423337 0.08400640 0.2736599
## [7,] 0.6200118 0.09508549 0.2849027
## [8,] 0.6200259 0.09462266 0.2853514
## [9,] 0.6005969 0.09944647 0.2999566
## [10,] 0.6029491 0.10122875 0.2958222
## [11,] 0.5908417 0.10240163 0.3067567
## [12,] 0.5899587 0.10514527 0.3048960
## [13,] 0.5854568 0.10485670 0.3096865
## [14,] 0.5812648 0.10718527 0.3115499
## [15,] 0.5811462 0.10702525 0.3118285
## [16,] 0.5762877 0.10825510 0.3154572
## [17,] 0.5771137 0.10868092 0.3142054
## [18,] 0.5737256 0.10898822 0.3172862
## [19,] 0.5736461 0.10974450 0.3166094
## [20,] 0.5722642 0.10965572 0.3180801
## [21,] 0.5711406 0.11033123 0.3185281
## [22,] 0.5710721 0.11027312 0.3186548
## [23,] 0.5696378 0.11064744 0.3197148
## [24,] 0.5699032 0.11076601 0.3193308
## [25,] 0.5688500 0.11086548 0.3202845
## [26,] 0.5688554 0.11109301 0.3200516
## [27,] 0.5684032 0.11106678 0.3205300
## [28,] 0.5680748 0.11127724 0.3206480
## [29,] 0.5680411 0.11125660 0.3207023
## [30,] 0.5675969 0.11137698 0.3210261
## [31,] 0.5676814 0.11141111 0.3209075
## [32,] 0.5673442 0.11144507 0.3212108
## [33,] 0.5673528 0.11151533 0.3211318
## [34,] 0.5672023 0.11150781 0.3212899
## [35,] 0.5671039 0.11157472 0.3213213
## [36,] 0.5670890 0.11156751 0.3213435
## [37,] 0.5669495 0.11160685 0.3214436
## [38,] 0.5669763 0.11161671 0.3214070
## [39,] 0.5668674 0.11162845 0.3215041
## [40,] 0.5668721 0.11165030 0.3214776
## [41,] 0.5668218 0.11164821 0.3215300
## [42,] 0.5667922 0.11166960 0.3215382
## [43,] 0.5667860 0.11166711 0.3215469
## [44,] 0.5667421 0.11168002 0.3215779
## [45,] 0.5667505 0.11168286 0.3215667
## [46,] 0.5667152 0.11168691 0.3215978
## [47,] 0.5667173 0.11169371 0.3215890
## [48,] 0.5667005 0.11169316 0.3216063
## [49,] 0.5666916 0.11170000 0.3216084
## [50,] 0.5666892 0.11169916 0.3216117var1_fevd_d2lm2<-fevd(var1, n.ahead=50)$IBM
var1_fevd_d2lm2## INPC IBM IDP
## [1,] 0.2815173 0.7184827 0.0000000
## [2,] 0.1211240 0.3923734 0.4865026
## [3,] 0.4512332 0.2283957 0.3203711
## [4,] 0.4119963 0.2079535 0.3800503
## [5,] 0.3956079 0.2124219 0.3919702
## [6,] 0.4064207 0.2078064 0.3857730
## [7,] 0.3900522 0.2015783 0.4083695
## [8,] 0.4039120 0.2024282 0.3936598
## [9,] 0.3880963 0.1987705 0.4131332
## [10,] 0.3973874 0.1993931 0.4032195
## [11,] 0.3912821 0.1971723 0.4115455
## [12,] 0.3919295 0.1971838 0.4108866
## [13,] 0.3931830 0.1964855 0.4103315
## [14,] 0.3893534 0.1957400 0.4149066
## [15,] 0.3930346 0.1958779 0.4110875
## [16,] 0.3891015 0.1949839 0.4159146
## [17,] 0.3916262 0.1952556 0.4131182
## [18,] 0.3898638 0.1946497 0.4154866
## [19,] 0.3901856 0.1946977 0.4151166
## [20,] 0.3904680 0.1944859 0.4150462
## [21,] 0.3894067 0.1942986 0.4162947
## [22,] 0.3904880 0.1943361 0.4151759
## [23,] 0.3893067 0.1940756 0.4166177
## [24,] 0.3900985 0.1941638 0.4157377
## [25,] 0.3895301 0.1939760 0.4164939
## [26,] 0.3896614 0.1939983 0.4163403
## [27,] 0.3897245 0.1939283 0.4163473
## [28,] 0.3894111 0.1938751 0.4167139
## [29,] 0.3897428 0.1938847 0.4163726
## [30,] 0.3893716 0.1938044 0.4168240
## [31,] 0.3896275 0.1938327 0.4165398
## [32,] 0.3894390 0.1937725 0.4167885
## [33,] 0.3894902 0.1937812 0.4167287
## [34,] 0.3895022 0.1937575 0.4167403
## [35,] 0.3894082 0.1937419 0.4168499
## [36,] 0.3895111 0.1937442 0.4167447
## [37,] 0.3893930 0.1937190 0.4168879
## [38,] 0.3894764 0.1937281 0.4167955
## [39,] 0.3894135 0.1937086 0.4168779
## [40,] 0.3894328 0.1937118 0.4168554
## [41,] 0.3894340 0.1937038 0.4168622
## [42,] 0.3894058 0.1936992 0.4168950
## [43,] 0.3894378 0.1936996 0.4168626
## [44,] 0.3894001 0.1936917 0.4169081
## [45,] 0.3894273 0.1936946 0.4168781
## [46,] 0.3894063 0.1936883 0.4169054
## [47,] 0.3894134 0.1936894 0.4168971
## [48,] 0.3894130 0.1936867 0.4169003
## [49,] 0.3894046 0.1936854 0.4169100
## [50,] 0.3894145 0.1936854 0.4169001var1_fevd_d2lm2d<-fevd(var1, n.ahead=50)$IMAXDP
var1_fevd_d2lm2d## NULLvar.2c.fevd <- fevd(var1, n.ahead = 12)
plot(var.2c.fevd)
#### Pruebas de estabilidad del modelo
var.2c.stabil <- stability(var1, type = "Rec-CUSUM")
plot(var.2c.stabil)
var.2c.stabil <- stability(var1, type = "OLS-CUSUM")
plot(var.2c.stabil)
var.2c.stabil <- stability(var1, type = "Rec-MOSUM")
plot(var.2c.stabil)
var.2c.stabil <- stability(var1, type = "OLS-MOSUM")
plot(var.2c.stabil)
var.2c.stabil <- stability(var1, type = "RE")
plot(var.2c.stabil)
var.2c.stabil <- stability(var1, type = "fluctuation")
plot(var.2c.stabil)Predicciones
var.2c.prd <- predict(var1, n.ahead = 8, ci = 0.95)
plot(var.2c.prd)
fanchart(var.2c.prd)
var.2c.prd ## $INPC
## fcst lower upper CI
## [1,] -12116937 -21444646 -2789228 9327709
## [2,] 21501169 7480849 35521489 14020320
## [3,] 3535326 -10733729 17804382 14269055
## [4,] -17206565 -32234240 -2178890 15027675
## [5,] 6765431 -9283718 22814580 16049149
## [6,] 14863490 -1437235 31164214 16300725
## [7,] -8712838 -25787547 8361871 17074709
## [8,] -6015669 -23167740 11136401 17152071
##
## $IBM
## fcst lower upper CI
## [1,] 8204821 -6219343 22628986 14424164
## [2,] -86654970 -112157029 -61152911 25502059
## [3,] 33482013 -7326915 74290941 40808928
## [4,] 67610629 24509056 110712201 43101573
## [5,] -47260859 -96599724 2078006 49338865
## [6,] -29229586 -79317375 20858203 50087789
## [7,] 61456137 7087486 115824789 54368651
## [8,] 9592308 -45963984 65148601 55556293
##
## $IDP
## fcst lower upper CI
## [1,] -715040712 -868645542 -561435883 153604830
## [2,] 468894001 162358899 775429103 306535102
## [3,] 433175251 116813537 749536965 316361714
## [4,] -557848371 -944622477 -171074265 386774106
## [5,] -125852363 -526295848 274591123 400443485
## [6,] 542404221 110596917 974211526 431807305
## [7,] -95122687 -548505043 358259669 453382356
## [8,] -405321332 -867961760 57319096 462640428library(forecast)## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo## Registered S3 methods overwritten by 'forecast':
## method from
## fitted.fracdiff fracdiff
## residuals.fracdiff fracdiffforecast(var1)## INPC
## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## Jan 2020 -12116937 -18215998 -6017876 -21444646 -2789228
## Feb 2020 21501169 12333774 30668563 7480849 35521489
## Mar 2020 3535326 -5794708 12865360 -10733729 17804382
## Apr 2020 -17206565 -27032633 -7380496 -32234240 -2178890
## May 2020 6765431 -3728543 17259405 -9283718 22814580
## Jun 2020 14863490 4205018 25521961 -1437235 31164214
## Jul 2020 -8712838 -19877390 2451714 -25787547 8361871
## Aug 2020 -6015669 -17230806 5199467 -23167740 11136401
## Sep 2020 12963936 1392636 24535236 -4732840 30660713
## Oct 2020 3003703 -8660996 14668401 -14835915 20843320
##
## IBM
## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## Jan 2020 8204821 -1226633 17636275 -6219343 22628986
## Feb 2020 -86654970 -103329870 -69980070 -112157029 -61152911
## Mar 2020 33482013 6798489 60165536 -7326915 74290941
## Apr 2020 67610629 39428025 95793232 24509056 110712201
## May 2020 -47260859 -79521809 -14999909 -96599724 2078006
## Jun 2020 -29229586 -61980231 3521059 -79317375 20858203
## Jul 2020 61456137 25906387 97005888 7087486 115824789
## Aug 2020 9592308 -26733999 45918615 -45963984 65148601
## Sep 2020 -46452133 -83906638 -8997628 -103733855 10829590
## Oct 2020 20368534 -18276224 59013291 -38733523 79470590
##
## IDP
## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## Jan 2020 -715040712 -815477512 -614603913 -868645542 -561435883
## Feb 2020 468894001 268461471 669326531 162358899 775429103
## Mar 2020 433175251 226317445 640033057 116813537 749536965
## Apr 2020 -557848371 -810746365 -304950376 -944622477 -171074265
## May 2020 -125852363 -387688284 135983559 -526295848 274591123
## Jun 2020 542404221 260060601 824747842 110596917 974211526
## Jul 2020 -95122687 -391573476 201328101 -548505043 358259669
## Aug 2020 -405321332 -707825648 -102817016 -867961760 57319096
## Sep 2020 262339271 -54900738 579579280 -222837455 747515997
## Oct 2020 256003657 -62642763 574650077 -231323989 743331302plot(forecast(var1,h=12))