Series de tiempo

Series de Tiempo

1. Instalar libreria

library(forecast)

## Warning: package 'forecast' was built under R version 4.1.3

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

2. Ejemplo Serie de Tiempo

produccion <- c(50,53,55,57,53,60)
serie_de_tiempo <- ts(data=produccion, start = c(2020,1), frequency = 4)
serie_de_tiempo

##      Qtr1 Qtr2 Qtr3 Qtr4
## 2020   50   53   55   57
## 2021   53   60

3. Crear el modelo ARIMA

ARIMA: Modelo Autoregresivo Integrado de Promedio Movil

modelo <- auto.arima(serie_de_tiempo, D = 1)
modelo

## Series: serie_de_tiempo 
## ARIMA(0,0,0)(0,1,0)[4] with drift 
## 
## Coefficients:
##        drift
##       1.2500
## s.e.  0.3536
## 
## sigma^2 = 8.01:  log likelihood = -4.22
## AIC=12.45   AICc=0.45   BIC=9.83

summary(modelo)

## Series: serie_de_tiempo 
## ARIMA(0,0,0)(0,1,0)[4] with drift 
## 
## Coefficients:
##        drift
##       1.2500
## s.e.  0.3536
## 
## sigma^2 = 8.01:  log likelihood = -4.22
## AIC=12.45   AICc=0.45   BIC=9.83
## 
## Training set error measures:
##                      ME     RMSE       MAE         MPE     MAPE      MASE
## Training set 0.03374998 1.155441 0.7004166 -0.01050981 1.247352 0.1400833
##                    ACF1
## Training set -0.5041734

4. Realizar el Pronostico

pronostico <- forecast(modelo, level = c(95), h = 5)
pronostico

##         Point Forecast    Lo 95    Hi 95
## 2021 Q3             60 54.45283 65.54717
## 2021 Q4             62 56.45283 67.54717
## 2022 Q1             58 52.45283 63.54717
## 2022 Q2             65 59.45283 70.54717
## 2022 Q3             65 57.15512 72.84488

plot(pronostico)