how can I make ARIMA more robust to outliers?

Question

I have a very noisy time series like this and I forcast future values with auto.arima from the forecast package in R:

set.seed(123)
y <- diffinv(rnorm(100))

plot(forecast(auto.arima(ts(y))))

I am quite happy with this forecast. However, in my data, sometimes extreme outliers can happen, for example:

y[100] <- -10

plot(forecast(auto.arima(ts(y))))

These completely destroy my forecast. How can I make it so that ARIMA is robust to those outliers or would I have to detect and remove these outliers separetly?

You may be interested in this answer and the tsoutliers package of R. — javlacalle, Aug 15 '18 at 20:30

score 1 · Accepted Answer · answered Aug 14 '18 at 07:05

1

ARIMA on its own can't really handle outliers. You need to use tsclean or some other similar preprocessing method.

answered Aug 14 '18 at 07:05

Skander H.

11,888
2
41
97

how can I make ARIMA more robust to outliers?

1 Answers1