Time series prediction using R

Question

I have the following R code

library(forecast)
value <- c(1.2, 1.7, 1.6, 1.2, 1.6, 1.3, 1.5, 1.9, 5.4, 4.2, 5.5, 6, 5.6, 
6.2, 6.8, 7.1, 7.1, 5.8, 0, 5.2, 4.6,         


        

Answer 1

auto.arima() returns the best ARIMA model according to either AIC, AICc or BIC value. Based on your 'value' dataset it has probably chosen an ARMA(1,0) or AR(1) model which as you can see tends to revert back to the mean very quickly. This will always happen with an AR(1) model in the long run and so it's not very useful if you want to predict more than a couple of steps ahead.

You could look at fitting a different type of model perhaps by analysing the acf and pacf of your value data. You would then need to check to see if your alternative model is a good fit for the data.