Forecast a model from the fable ATA model

# S3 method for ATA
forecast(
  object,
  new_data,
  h = NULL,
  ci_level = 95,
  negative_forecast = TRUE,
  onestep = FALSE,
  ...
)

Arguments

object: The time series model used to produce the forecasts
new_data: A `tsibble` containing future information used to forecast.
h: The forecast horison (can be used instead of `new_data` for regular time series with no exogenous regressors).
ci_level: Confidence Interval levels for forecasting. Default value is 95.
negative_forecast: Negative values are allowed for forecasting. Default value is TRUE. If FALSE, all negative values for forecasting are set to 0.
onestep: Default is FALSE. if TRUE, the dynamic forecast strategy uses a one-step model multiple times `h` forecast horizon) where the prediction for the prior time step is used as an input for making a prediction on the following time step.
...: Other arguments

Value

A vector of fitted residuals.

Examples

library(fable.ata)
as_tsibble(USAccDeaths) %>%
  model(ata = AutoATA(value ~ trend("A") + season("M"))) %>% forecast(h=24)
#> # A fable: 24 x 4 [1M]
#> # Key:     .model [1]
#>    .model    index    value  .mean
#>    <chr>     <mth>   <dist>  <dbl>
#>  1 ata    1979 Jan 8091.851  8092.
#>  2 ata    1979 Feb 7352.286  7352.
#>  3 ata    1979 Mar 8154.435  8154.
#>  4 ata    1979 Apr 8387.586  8388.
#>  5 ata    1979 May 9272.331  9272.
#>  6 ata    1979 Jun 9691.667  9692.
#>  7 ata    1979 Jul 10632.91 10633.
#>  8 ata    1979 Aug 9921.513  9922.
#>  9 ata    1979 Sep  8799.18  8799.
#> 10 ata    1979 Oct 9183.734  9184.
#> # ℹ 14 more rows