Extract residuals from a fable model

Extracts the residuals.

# S3 method for ARIMA
residuals(object, type = c("innovation", "regression"), ...)

Arguments

object	The time series model used to produce the forecasts
type	The type of residuals to extract.
...	Additional arguments for forecast model methods.

Value

A vector of fitted residuals.

Examples

USAccDeaths %>%
  as_tsibble() %>%
  model(arima = ARIMA(log(value) ~ pdq(0, 1, 1) + PDQ(0, 1, 1))) %>%
  residuals()
#> # A tsibble: 72 x 3 [1M]
#> # Key:       .model [1]
#>    .model    index   .resid
#>    <chr>     <mth>    <dbl>
#>  1 arima  1973 Jan 0.00526 
#>  2 arima  1973 Feb 0.00227 
#>  3 arima  1973 Mar 0.00157 
#>  4 arima  1973 Apr 0.00119 
#>  5 arima  1973 May 0.00103 
#>  6 arima  1973 Jun 0.000930
#>  7 arima  1973 Jul 0.000837
#>  8 arima  1973 Aug 0.000683
#>  9 arima  1973 Sep 0.000512
#> 10 arima  1973 Oct 0.000482
#> # … with 62 more rows