“Pronósticos”

Instalar paquetes

# install.packages("forecast")
library(forecast)

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

Crear Serie de tiempo

produccion <-c(19,18,15,20,18,22,20)
produccion_st <-ts(data= produccion, start = c(2022,2), frequency = 12)
produccion_st

##      Feb Mar Apr May Jun Jul Aug
## 2022  19  18  15  20  18  22  20

Arima: Modelo Autorregresivo Integrado de Media Movil (AurtoRegressive Integrated Moving Average)

Arima (p,d,q)

p = orden de auto-regresion

d = orden de integracion

q = orden de promedio movil

modelo <-auto.arima(produccion_st)
modelo

## Series: produccion_st 
## ARIMA(0,0,0) with non-zero mean 
## 
## Coefficients:
##          mean
##       18.8571
## s.e.   0.7674
## 
## sigma^2 = 4.81:  log likelihood = -14.89
## AIC=33.78   AICc=36.78   BIC=33.67

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

##          Point Forecast    Lo 95    Hi 95
## Sep 2022       18.85714 14.55882 23.15547
## Oct 2022       18.85714 14.55882 23.15547
## Nov 2022       18.85714 14.55882 23.15547
## Dec 2022       18.85714 14.55882 23.15547
## Jan 2023       18.85714 14.55882 23.15547

plot(pronostico)