search

ellisp / forecastHybrid

Convenient functions for ensemble forecasts in R combining approaches from the {forecast} package
GNU General Public License v3.0
79 stars 23 forks source link

Adding ARFIMA models. #93

Open ASLlohmann opened 4 years ago

ASLlohmann commented 4 years ago

I would be nice to add the arfima model from forecast package.

Such "model" are quite uncommon but are working quite well for times series that have long rum memory such as consumer/Producer price indexes. Especially in some countries where there is mid-month divulgations.

I think it would be quite easy, just changing a few lines of code. 

 models <- c("a" = auto.arima, "e" = ets, "f" = thetam, "n" = nnetar,
              "s" = stlm, "t" = tbats, "z" = snaive)                  "s" = stlm, "t" = tbats, "z" = snaive, "x"=arfima)

validModels <- c("a", "e", "f", "n", "s", "t", "z", "x")

It is working on my computer. The only problem is an error message when I run thecvts function with a hybridModelthat include a "x" component.

Error in { : task 1 failed - "'data' must be of a vector type, was 'NULL'"

Any ideas ?