tscalibrate: Walk Forward Calibration of Distribution Variance...

In tsmodels/tsissm: Linear Innovations State Space Unobserved Components Model

Walk Forward Calibration of Distribution Variance (Experimental)

Description

Using an expanding window walk forward backtest, provides a calibrated set of adjustment values which can be used in the predict function for scaling the multi-horizon distributional standard deviation.

Usage

## S3 method for class 'tsissm.spec'
tscalibrate(
  object,
  start = floor(length(object$target$y_orig))/2,
  end = length(object$target$y_orig),
  h = 1,
  nsim = 5000,
  solver = "nlminb",
  autodiff = TRUE,
  autoclean = FALSE,
  trace = FALSE,
  ...
)

Arguments

object	an object of class “tsissm.spec”.
start	numeric data index from which to start the backtest calibration.
end	numeric data index on which to end the backtest. The backtest will end 1 period before that date in order to have at least 1 out of sample value to compare against.
h	forecast horizon. As the expanding window approaches the “end”, the horizon will automatically shrink to the number of available out of sample periods.
nsim	number of samples to draw for the simulated prediction distribution.
solver	solver to use.
autodiff	whether to use automatic differentiation for estimation. This makes use of the tsissmad package.
autoclean	whether to perform automatic cleaning on the training data prior to prediction as per the ‘auto_clean’ function in the tsaux package.
trace	whether to show the progress bar. The user is expected to have set up appropriate handlers for this using the “progressr” package.
...	Additional arguments passed to the “auto_clean” function.

Value

A list with the following data.tables:

• sample : multi-horizon white noise sample

• sigma_scale: The scaling values per horizon which can be used to scale the predictive distribution standard deviation.

• sd_sigma_scale: The standard deviation of the sigma scaling factor

Note

The walk forward predictive errors per horizon are used to estimate the realized variance against the expected variance (sigma_scale). A jackknife procedure is used for estimating the mean of this value. The output also includes samples from a kernel fitted on the whitened errors per horizon which can then be used as inputs to the prediction function. The function can use parallel functionality as long as the user has set up a plan using the future package.

tsmodels/tsissm documentation built on Oct. 15, 2022, 6:44 a.m.