library(readxl)
Base_Dinero <- read_excel("BaseDeDatos.xlsx", sheet = "Datos")
head(Base_Dinero)#dinero.ts = ts(Base_Dinero, start=2000, frequency=12)
#plot(dinero.ts)tcr.ts=ts(Base_Dinero$tcr,start=2008,frequency=12)
tc.ts=ts(Base_Dinero$tc,start=2008,frequency=12)
inf.ts=ts(Base_Dinero$inf,start=2008,frequency=12)
brecha_pib.ts=ts(Base_Dinero$brecha_pib,start=2008,frequency=12)
brecha_inf.ts=ts(Base_Dinero$brecha_inf,start=2008,frequency=12)
igae.ts=ts(Base_Dinero$igae,start=2008,frequency=12)
tasaO.ts=ts(Base_Dinero$tasaO,start=2008,frequency=12)
rend_bon.ts=ts(Base_Dinero$rend_bon,start=2008,frequency=12)
fed.ts=ts(Base_Dinero$fed,start=2008,frequency=12)m2 = lm(tasaO.ts ~ brecha_inf.ts + rend_bon.ts + tc.ts)
summary(m2)##
## Call:
## lm(formula = tasaO.ts ~ brecha_inf.ts + rend_bon.ts + tc.ts)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.54598 -0.72698 0.09437 0.82582 2.20520
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.30285 0.47515 -9.056 < 2e-16 ***
## brecha_inf.ts -0.15393 0.06565 -2.345 0.02006 *
## rend_bon.ts 1.38705 0.06108 22.709 < 2e-16 ***
## tc.ts 0.07349 0.02254 3.260 0.00132 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.05 on 192 degrees of freedom
## Multiple R-squared: 0.804, Adjusted R-squared: 0.8009
## F-statistic: 262.5 on 3 and 192 DF, p-value: < 2.2e-16library(forecast)## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoopib.ts_arima=auto.arima(brecha_pib.ts, stepwise=FALSE, approximation=FALSE)
summary(pib.ts_arima)## Series: brecha_pib.ts
## ARIMA(1,0,3) with zero mean
##
## Coefficients:
## ar1 ma1 ma2 ma3
## 0.8449 0.1145 0.1003 -0.3113
## s.e. 0.0704 0.1001 0.0891 0.1078
##
## sigma^2 = 2.722: log likelihood = -375
## AIC=760 AICc=760.32 BIC=776.39
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set -0.003199852 1.632785 0.5700529 21.65207 46.02203 0.2422843
## ACF1
## Training set -0.01824328tc.ts_arima=auto.arima(tc.ts, stepwise = FALSE, approximation = FALSE)
summary(tc.ts_arima)## Series: tc.ts
## ARIMA(0,1,0)
##
## sigma^2 = 0.4187: log likelihood = -191.8
## AIC=385.61 AICc=385.63 BIC=388.88
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set 0.03225329 0.6453981 0.4365655 0.1684118 2.574994 0.2924412
## ACF1
## Training set 0.005354766brecha_inf.ts_arima=auto.arima(brecha_inf.ts, stepwise = FALSE, approximation = FALSE)
summary(brecha_inf.ts_arima)## Series: brecha_inf.ts
## ARIMA(1,1,0)(2,0,2)[12]
##
## Coefficients:
## ar1 sar1 sar2 sma1 sma2
## 0.3987 0.4355 -0.2244 -1.4279 0.6598
## s.e. 0.0692 0.1946 0.1029 0.2035 0.2245
##
## sigma^2 = 0.06383: log likelihood = -16.1
## AIC=44.19 AICc=44.64 BIC=63.83
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set 0.02041485 0.2487423 0.1840467 225.1235 290.8491 0.1270269
## ACF1
## Training set 0.01306303rend_bon.ts_arima=auto.arima(rend_bon.ts, stepwise = FALSE, approximation = FALSE)
summary(rend_bon.ts_arima)## Series: rend_bon.ts
## ARIMA(0,1,0)(1,0,1)[12]
##
## Coefficients:
## sar1 sma1
## -0.6687 0.8532
## s.e. 0.1295 0.1044
##
## sigma^2 = 0.1306: log likelihood = -78.43
## AIC=162.87 AICc=162.99 BIC=172.69
##
## Training set error measures:
## ME RMSE MAE MPE MAPE MASE
## Training set 0.01493576 0.3586097 0.2685993 0.03862169 4.118367 0.2657497
## ACF1
## Training set -0.05078733f_pib.ts=forecast(pib.ts_arima,h=2)
f_pib.ts1 = -0.03351422
f_pib.ts2 = -0.05402005
f_tc.ts=forecast(tc.ts_arima, h=2)
f_tc.ts1=17.1552
f_tc.ts2=17.1552
f_brecha_inf.ts=forecast(brecha_inf.ts_arima,h=2)
f_brecha_inf.ts1=2.230971
f_brecha_inf.ts2=2.643418
f_rend_bon.ts=forecast(rend_bon.ts_arima,h=2)
f_rend_bon.ts## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## May 2024 10.56240 10.09919 11.02561 9.853983 11.27081
## Jun 2024 10.53954 9.88447 11.19462 9.537695 11.54139f_rend_bon.ts1=10.56240
f_rend_bon.ts2=10.53954pronosticoM2M = -4.30285 - 0.15393 *(f_brecha_inf.ts1) + 1.38705*(f_rend_bon.ts1) + 0.07349*(f_tc.ts1)
pronosticoM2M## [1] 11.26505pronosticoM2J = -4.30285 - 0.15393 *(f_brecha_inf.ts2) + 1.38705*(f_rend_bon.ts2) + 0.07349*(f_tc.ts2)
pronosticoM2J## [1] 11.16985#MODELO
m3 = lm(tasaO.ts ~ brecha_inf.ts + rend_bon.ts + tc.ts + brecha_pib.ts)
summary(m3)##
## Call:
## lm(formula = tasaO.ts ~ brecha_inf.ts + rend_bon.ts + tc.ts +
## brecha_pib.ts)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.53071 -0.74140 0.05002 0.81156 2.20071
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.14633 0.47956 -8.646 2.14e-15 ***
## brecha_inf.ts -0.13148 0.06634 -1.982 0.048909 *
## rend_bon.ts 1.34901 0.06404 21.066 < 2e-16 ***
## tc.ts 0.07724 0.02249 3.435 0.000727 ***
## brecha_pib.ts 0.04809 0.02583 1.862 0.064147 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.043 on 191 degrees of freedom
## Multiple R-squared: 0.8075, Adjusted R-squared: 0.8034
## F-statistic: 200.3 on 4 and 191 DF, p-value: < 2.2e-16pronosticoM3M = -4.14633 - 0.13148 *(f_brecha_inf.ts1) + 1.34901*(f_rend_bon.ts1) + 0.07724*(f_tc.ts1) + 0.04809*(f_pib.ts1)
pronosticoM3M## [1] 11.13258pronosticoM3J = -4.14633 - 0.13148 *(f_brecha_inf.ts2) + 1.34901*(f_rend_bon.ts2) + 0.07724*(f_tc.ts2) + 0.04809*(f_pib.ts2)
pronosticoM3J## [1] 11.04653